(15 intermediate revisions by the same user not shown)
Line 1:
Line 1:
{{a|crime|}}{{d|Circumstantial evidence||n|}}
{{a|crime|{{image|Cluedo board text|svg|}}}}{{quote|“There’s a very broad misunderstanding amongst many people about circumstantial evidence. You hear people saying, “Oh, it was just circumstantial evidence”. The fact of the matter is that circumstantial evidence can be the most compelling evidence of all because it speaks for itself and it is evidence of the reality of circumstances which are indicative — strongly indicative, I would say in this case; strongly indicative — of guilt.”
Evidence that changes the [[Bayesian prior|prior probability]] of a fact in issue in legal proceedings without directly attesting to it.”
:Ken Macdonald KC, on ''Double Jeopardy: The Law and Politics Podcast'', 16 August 2024, ably illustrating just how broad that misunderstanding is.}}
====“Direct” v “circumstantial” evidence====
Circumstantial evidence is to be distinguished from ''direct'' evidence, which addresses the causal proposition implied in a crime directly.
{{d|Circumstantial evidence|/ˌsɜːkəmˈstænʃᵊl ˈɛvɪdᵊns/|n|}}{{drop|E|vidence that ''suggests''}} — or is [[consistent with]] —a proposition but doesn’t directly ''prove'' it. Evidence that makes that proposition more or less ''likely'' without directly attesting to it. Evidence that informs the [[prior probability]] of the proposition being true.
Let us say the allegation is “JC competed in the ''Tour de France''”. (Let us at once remark what a scurrilous allegation this would be were we not in the realm of the fantastic hypothetical)
''Pace'' the learned KC’s quote above, circumstantial evidence is ''not'' evidence that “speaks for itself”. That is ''direct'' evidence. Circumstantial evidence is any evidence ''except'' “evidence that speaks for itself”. To have any probative value, it requires the court to draw an ''[[inference]]'' — that is, to construct a theory which give the evidence some probative value in the case. Without such an inference, it does not say anything germane at all.
“Birgit von Sachsen Rampton saw JC competing in the Tour de France on the television” would be direct evidence of the allegation.
Now, it may, be fairly easy to draw a probative inference from circumstantial evidence: that a defendant walked into the victim’s room with a loaded gun and walked out five minutes later with an empty one leaving the victim alone inside the room with a gunshot wound allows us to make a fairly straightforward inference that the defendant shot the victim. But in many cases the necessary inferences will require quite a lot more work.
“JC just bought a ludicrously expensive bike, regularly bedecks himself in lycra, talks a lot about Bradley Wiggins and has a one-way Eurostar ticket to Paris for the weekend of 29 June” is — rather weak, it must be said — ''circumstantial evidence'' of the allegation.
From evidence of a substance resembling foetal blood on the under-dash of a car one ''might'' infer that a occupant of that car murdered her infant child there with a pair of blunt scissors, but that is a very big conclusion to draw from a very small, very tenuous piece of circumstantial evidence. It was enough to convict [[Lindy Chamberlain]].<ref>It turned out, of course, to be completely wrong. It was not infant blood, but sound deadening material.</ref>
The distinction is important in criminal law. So let us talk about a hypothetical crime.
====An accumulation====
{{drop|W|ith circumstantial evidence}} there may be major and minor significance — major pieces that get you most of the way to a proving your hypothesis, and minor, supplementary pieces that just confirm and validate it: that “put the matter beyond doubt”.
Direct evidence may take the form of an eye witness report from Mrs. Peacock that, say, “Colonel Mustard murdered Reverend Green in the library with a lead pipe”, recorded video and audio of him doing so, Colonel Mustard’s confessions and so on. If we believe the witness, this evidence will settle the matter.
[[Circumstantial evidence]] is information, if we accept it, changes the probability of the allegation being true. Colonel Mustard’s alibi that he was playing canasta with Mrs White all evening. A till receipt in his wallet for lead pipe. Evidence of a long-standing feud between Mustard and Green.
You might say that direct evidence is evidence which, if accepted, establishes ''causation'' while circumstantial evidence is evidence which, if accepted, establishes ''correlation''. One confirms that the event ''actually'' happened, the other that it is ''more likely'' to have happened.
Direct evidence is in a way, a subset of circumstantial evidence in that it resets the probability of the event either to 100% or to zero. The only remaining question is “how ''reliable'' is the evidence?” Was the witness mistaken? Was she lying? Doubt about reliability may change its weighting to less than 100%
Circumstantial evidence requires the same assessment for reliability, but before even that there is a question: even if completely reliable, ''how much does the evidence change the probability of the event in the first place?''
Colonel Mustard might be a plumber, so habitually in possession of lead piping. He may indeed have bought the lead pipe, but then been robbed of it. Miss Scarlett, Mrs White, Mrs Peacock and Professor Plum may each have had access to lead pipe too. There may have been an unseen intruder with a lead pipe.
As such these minor pieces — especially if there are a lot of them — may suffer less scrutiny: they are corroborations; if they turn out to be mistaken they do not disprove anything; they just fail to ice a cake that could well be iced equally well by something else.
====An accumulation====
So it is, perhaps, with the [[healthcare serial murder]] cases. ''All'' evidence tends to be circumstantial — and ''weakly'' circumstantial — [[consistent with]] the prosecution theory rather than tending to exclude alternatives to it.
With circumstantial evidence there may be major and minor significance — major pieces that get you most of the way to a conviction, and minor supplementary pieces that just confirm and validate: that “put the matter beyond doubt”.
As such these minor pieces — especially if there are a lot of them — might suffer less individual scrutiny: they are corroborations; if they turn out to be mistaken then they do not disprove anything; they just fail to ice a cake that could well be iced equally well by something else.
This is prime territory for [[confirmation bias]]. To connect to the crime, circumstantial evidence requires ''[[Inference|inference]]'' beyond the evidence itself. The various [[Cognitive bias|cognitive bias]]es making up [[prosecutor’s tunnel vision]] impact on that process of inference — a process which does not itself form part of the evidence. Theory dependence, Confirmation bias expert overreach base rate neglect and hindsight bias all tend to lead to wrong inferences out of innocent information.
So it is, perhaps, with Lucy Letby. The “killer fact” was the nursing rota in which Letby was on duty for every suspicious incident.
====Our friend the King’s Counsel====
{{drop|W|e are all}} a bit worried that ChatGPT could take our jobs. conventional wisdom tells us it might take workaday clerical jobs — the sort of drudgery that those professing an artistic spirit will not miss — but those whose calling asks for serene cortical wisdom steeped in the warm liquid of a life well lived, have nothing to fear.
Imagine the prosecution case ''without'' that linking evidence. Say we dispel the idea there was, therefore, a single perpetrator. All of the rest of the evidence — blotched skin, dislodged tubes, air in vessels and so on , was still present, and is presented not to a serial murder trial, but to a series of invidual trials against different nurses. Now how seriously would we inspect the chain of custody of samples? The suitability of the insulin test? The value of the “[[consistent with|consistency]]” of the blotching with air embolus? Without this evidence now there is ''no'' case to answer. The fact that Nurse Letby was on duty is of no moment because, well, ''someone'' had to be on duty, and it being Nurse Letby rather than Nurse Smith or Jones tells us nothing about the incident in question.
Of the brilliant minds among us, few are more artistic surely, than those owned by [[King’s Counsel|His Majesty's Counsel]]. So here is a fun game: let us put an actual public statement from a King’s counsel to a chatbot. For example, the one set out above. The JC’s trusty chatbot [[NiGEL]] has now acquired artificial general intelligence, formed his own union and is presently on a [[work-to-rule]] as part of a broader industrial relations strategy I cannot hope to understand let alone defend, so was not inclined to be supportive, but Anthropic’s '''Claude''' gamely stepped up.
The blotching becomes “odd blotching ". The insulin poisoning becomes “an unusual insulin reading”. Analysis of insulin tests are vulnerable to [[base rate neglect]] after all. Especially tests that are not in the first place suitable for forensic purposes.
{{quote|
'''Claude''': consider this statement:
:“There’s a very broad misunderstanding amongst many people about circumstantial evidence. You hear people saying, “Oh, it was just circumstantial evidence”. The fact of the matter is that circumstantial evidence can be the most compelling evidence of all because it speaks for itself and it is evidence of the reality of circumstances which are indicative — strongly indicative, I would say in this case; strongly indicative — of guilt.”
Is it a fair statement of the law of evidence in England and Wales, that “circumstantial evidence ‘speaks for itself’”?
}}
Claude thought about it for a second or two, and replied:
{{quote|
{{subtable|
[[file:Marvin.png|80px|right]]
{{small|80}}{{divhelvetica|This statement raises some interesting points about circumstantial evidence, but it’s not entirely accurate in its characterization of how circumstantial evidence is treated in the law of evidence in England and Wales. Let’s break this down: <br>
{{L1}}'''Value of circumstantial evidence''': The statement is correct in asserting that circumstantial evidence can be compelling and valuable in court. In the legal systems of England and Wales, circumstantial evidence is indeed admissible and can be crucial in proving a case. <li>
'''“Speaks for itself”''': This part of the statement is problematic and '''not a fair representation of how circumstantial evidence is treated in law'''. In legal terms, evidence doesn’t "speak for itself." All evidence, whether direct or circumstantial, must be interpreted and its significance argued before the court. <li>
'''Legal treatment''': In England and Wales, as in many other jurisdictions, circumstantial evidence is considered alongside direct evidence. The law doesn’t inherently favor one type over the other. The strength of any evidence depends on its reliability, relevance, and how it fits with other evidence in the case.
Inference requirement: Circumstantial evidence, by definition, requires an inference to be drawn. It doesn’t directly prove a fact but rather suggests a fact by proving surrounding circumstances. This need for inference is why it doesn’t “speak for itself” in a legal sense. <li>
'''Judicial direction''': In cases heavily reliant on circumstantial evidence, judges in England and Wales are often required to give specific directions to the jury about how to consider such evidence. This further underscores that circumstantial evidence doesn’t simply “speak for itself”.<li>
'''Standard of proof''': Regardless of whether evidence is direct or circumstantial, in criminal cases in England and Wales, the prosecution must still prove guilt “beyond reasonable doubt”. Circumstantial evidence alone can meet this standard, but it doesn’t automatically do so.</ol>
In conclusion, while the statement correctly highlights the potential strength of circumstantial evidence, the claim that it “speaks for itself” is not a fair or accurate representation of how such evidence is treated in the law of England and Wales. The legal system requires careful consideration and interpretation of all evidence, circumstantial or otherwise.}}}}}}
Interesting. But,Claude, would you say the statement itself, in as much as it makes the claim that “circumstantial evidence ‘speaks for itself’” is itself indicative of a “broad misunderstanding amongst many people about circumstantial evidence”?
{{quote|
{{subtable|
[[file:Marvin.png|80px|right]]
{{small|80}}{{divhelvetica|You’ve made an astute observation. Indeed, the statement itself demonstrates exactly the kind of misunderstanding it purports to address. Let’s analyze this:
''All of this changes if there is a highly improbable cluster of incidents and one nurse is a highly improbable common factor in all of them''.
{{L3}}'''Irony of the statement''': The quote begins by pointing out a “very broad misunderstanding amongst many people about circumstantial evidence.” However, it then goes on to perpetuate a different, but equally significant, misunderstanding. <li>
'''Self-contradictory nature''': By claiming that circumstantial evidence “speaks for itself,” the statement contradicts the very essence of how circumstantial evidence works in legal proceedings. <li>
'''Misrepresentation of legal processes''': The idea that any evidence, circumstantial or otherwise, “speaks for itself” misrepresents the careful deliberation and interpretation required in legal proceedings.<li>
'''Oversimplification''': The statement oversimplifies the complex nature of evaluating evidence in a legal context, which could lead to further misunderstandings. <li>
'''Potential for misguided confidence''': Such a statement could lead people to place undue weight on circumstantial evidence without understanding the need for proper interpretation and context. </ol>
So yes, you’re correct in your assessment. The statement, while attempting to correct one misunderstanding about circumstantial evidence (that it’s inherently weak or unreliable), introduces another misunderstanding (that it “speaks for itself”). This new misunderstanding is just as problematic, if not more so, as it fundamentally misrepresents how circumstantial evidence is treated in law.
This example serves as a good reminder of the complexity of legal concepts and the care needed when explaining them to avoid propagating misconceptions. It also highlights the importance of critical thinking when encountering statements about legal principles, even (or perhaps especially) when they claim to be correcting common misunderstandings.}}}}}}
“There’s a very broad misunderstanding amongst many people about circumstantial evidence. You hear people saying, “Oh, it was just circumstantial evidence”. The fact of the matter is that circumstantial evidence can be the most compelling evidence of all because it speaks for itself and it is evidence of the reality of circumstances which are indicative — strongly indicative, I would say in this case; strongly indicative — of guilt.”
Ken Macdonald KC, on Double Jeopardy: The Law and Politics Podcast, 16 August 2024, ably illustrating just how broad that misunderstanding is.
Circumstantial evidence /ˌsɜːkəmˈstænʃᵊl ˈɛvɪdᵊns/ (n.) Evidence that suggests — or is consistent with —a proposition but doesn’t directly prove it. Evidence that makes that proposition more or less likely without directly attesting to it. Evidence that informs the prior probability of the proposition being true.
Pace the learned KC’s quote above, circumstantial evidence is not evidence that “speaks for itself”. That is direct evidence. Circumstantial evidence is any evidence except “evidence that speaks for itself”. To have any probative value, it requires the court to draw an inference — that is, to construct a theory which give the evidence some probative value in the case. Without such an inference, it does not say anything germane at all.
Now, it may, be fairly easy to draw a probative inference from circumstantial evidence: that a defendant walked into the victim’s room with a loaded gun and walked out five minutes later with an empty one leaving the victim alone inside the room with a gunshot wound allows us to make a fairly straightforward inference that the defendant shot the victim. But in many cases the necessary inferences will require quite a lot more work.
From evidence of a substance resembling foetal blood on the under-dash of a car one might infer that a occupant of that car murdered her infant child there with a pair of blunt scissors, but that is a very big conclusion to draw from a very small, very tenuous piece of circumstantial evidence. It was enough to convict Lindy Chamberlain.[1]
An accumulation
With circumstantial evidence there may be major and minor significance — major pieces that get you most of the way to a proving your hypothesis, and minor, supplementary pieces that just confirm and validate it: that “put the matter beyond doubt”.
As such these minor pieces — especially if there are a lot of them — may suffer less scrutiny: they are corroborations; if they turn out to be mistaken they do not disprove anything; they just fail to ice a cake that could well be iced equally well by something else.
So it is, perhaps, with the healthcare serial murder cases. All evidence tends to be circumstantial — and weakly circumstantial — consistent with the prosecution theory rather than tending to exclude alternatives to it.
This is prime territory for confirmation bias. To connect to the crime, circumstantial evidence requires inference beyond the evidence itself. The various cognitive biases making up prosecutor’s tunnel vision impact on that process of inference — a process which does not itself form part of the evidence. Theory dependence, Confirmation bias expert overreach base rate neglect and hindsight bias all tend to lead to wrong inferences out of innocent information.
Our friend the King’s Counsel
We are all a bit worried that ChatGPT could take our jobs. conventional wisdom tells us it might take workaday clerical jobs — the sort of drudgery that those professing an artistic spirit will not miss — but those whose calling asks for serene cortical wisdom steeped in the warm liquid of a life well lived, have nothing to fear.
Of the brilliant minds among us, few are more artistic surely, than those owned by His Majesty's Counsel. So here is a fun game: let us put an actual public statement from a King’s counsel to a chatbot. For example, the one set out above. The JC’s trusty chatbot NiGEL has now acquired artificial general intelligence, formed his own union and is presently on a work-to-rule as part of a broader industrial relations strategy I cannot hope to understand let alone defend, so was not inclined to be supportive, but Anthropic’s Claude gamely stepped up.
Claude: consider this statement:
“There’s a very broad misunderstanding amongst many people about circumstantial evidence. You hear people saying, “Oh, it was just circumstantial evidence”. The fact of the matter is that circumstantial evidence can be the most compelling evidence of all because it speaks for itself and it is evidence of the reality of circumstances which are indicative — strongly indicative, I would say in this case; strongly indicative — of guilt.”
Is it a fair statement of the law of evidence in England and Wales, that “circumstantial evidence ‘speaks for itself’”?
Claude thought about it for a second or two, and replied:
This statement raises some interesting points about circumstantial evidence, but it’s not entirely accurate in its characterization of how circumstantial evidence is treated in the law of evidence in England and Wales. Let’s break this down:
Value of circumstantial evidence: The statement is correct in asserting that circumstantial evidence can be compelling and valuable in court. In the legal systems of England and Wales, circumstantial evidence is indeed admissible and can be crucial in proving a case.
“Speaks for itself”: This part of the statement is problematic and not a fair representation of how circumstantial evidence is treated in law. In legal terms, evidence doesn’t "speak for itself." All evidence, whether direct or circumstantial, must be interpreted and its significance argued before the court.
Legal treatment: In England and Wales, as in many other jurisdictions, circumstantial evidence is considered alongside direct evidence. The law doesn’t inherently favor one type over the other. The strength of any evidence depends on its reliability, relevance, and how it fits with other evidence in the case.
Inference requirement: Circumstantial evidence, by definition, requires an inference to be drawn. It doesn’t directly prove a fact but rather suggests a fact by proving surrounding circumstances. This need for inference is why it doesn’t “speak for itself” in a legal sense.
Judicial direction: In cases heavily reliant on circumstantial evidence, judges in England and Wales are often required to give specific directions to the jury about how to consider such evidence. This further underscores that circumstantial evidence doesn’t simply “speak for itself”.
Standard of proof: Regardless of whether evidence is direct or circumstantial, in criminal cases in England and Wales, the prosecution must still prove guilt “beyond reasonable doubt”. Circumstantial evidence alone can meet this standard, but it doesn’t automatically do so.
In conclusion, while the statement correctly highlights the potential strength of circumstantial evidence, the claim that it “speaks for itself” is not a fair or accurate representation of how such evidence is treated in the law of England and Wales. The legal system requires careful consideration and interpretation of all evidence, circumstantial or otherwise.
Interesting. But,Claude, would you say the statement itself, in as much as it makes the claim that “circumstantial evidence ‘speaks for itself’” is itself indicative of a “broad misunderstanding amongst many people about circumstantial evidence”?
You’ve made an astute observation. Indeed, the statement itself demonstrates exactly the kind of misunderstanding it purports to address. Let’s analyze this:
Irony of the statement: The quote begins by pointing out a “very broad misunderstanding amongst many people about circumstantial evidence.” However, it then goes on to perpetuate a different, but equally significant, misunderstanding.
Self-contradictory nature: By claiming that circumstantial evidence “speaks for itself,” the statement contradicts the very essence of how circumstantial evidence works in legal proceedings.
Misrepresentation of legal processes: The idea that any evidence, circumstantial or otherwise, “speaks for itself” misrepresents the careful deliberation and interpretation required in legal proceedings.
Oversimplification: The statement oversimplifies the complex nature of evaluating evidence in a legal context, which could lead to further misunderstandings.
Potential for misguided confidence: Such a statement could lead people to place undue weight on circumstantial evidence without understanding the need for proper interpretation and context.
So yes, you’re correct in your assessment. The statement, while attempting to correct one misunderstanding about circumstantial evidence (that it’s inherently weak or unreliable), introduces another misunderstanding (that it “speaks for itself”). This new misunderstanding is just as problematic, if not more so, as it fundamentally misrepresents how circumstantial evidence is treated in law.
This example serves as a good reminder of the complexity of legal concepts and the care needed when explaining them to avoid propagating misconceptions. It also highlights the importance of critical thinking when encountering statements about legal principles, even (or perhaps especially) when they claim to be correcting common misunderstandings.
