Claim

Embedding a well-log-based sweet-spot index as a geological prior in an attention-gated KG-SE-ResNet18 model improved reservoir-type classification accuracy from 86.95% to 89.28% in the Jiyuan Oilfield case study.

Type QUANTITATIVE · truth-evaluable: yes · status at snapshot: ACTIVE · created seq 17506 · qualifiers {"model":"KG-SE-ResNet18","location":"Jiyuan Oilfield, western Ordos Basin, China","material":"Chang 8 Member tight sandstone","comparison":"86.95% baseline versus 89.28% knowledge-guided accuracy","source_edition":"94d38610-5a0c-8c12-94d8-4d35234b513e"}

28 words; atomic claims are usually under 25

Referenced 123 times: checked 3, looked up by assistants 0, viewed 71, shared 49. A count of attention, not evidence.

Topics

Technology · 1efd24fe Earth science · 1efd24fe

Assessment

Supported

Score: 0.9734 under ledger-default@0.3.0 at snapshot 27745

3 of 4 review checks done · 1 counted · 2 by the author only

2 independent evidence lineages · review checks 1 of 4 · stability HIGH

Main unresolved issue: 5 counted evidence items have no independence review; repeats of one origin may be counted as several coverage:ea80e47e-f54e-8d61-9f24-378fb9a2d99e

Not yet independently audited.Evidence reviewed so far supports this claim, but only 1 of 4 review checks has been done.A quoted passage from matilda.science was not found on the page when Galedra fetched it.

Why?

Strongest counted support: The primary Scientific Reports study directly reports the geological-prior attention model and its 86.95%-to-89.28% classification improvement. weight 1.800000 evidence

Suppressed as dependent: The indexed Matilda record reproduces the geological-prior mechanism and accuracy increase from 86.95% to 89.28%.; The study reports classification improvement from 86.95% to 89.28% after embedding the geological prior.; The passage directly reports the geological prior and accuracy improvement from 86.95% to 89.28%.

Review gaps: qualifiers reviewed, opposing search done, independence reviewed

What would most change this: One independent, direct measurement that contradicts this claim would move it from Supported to Supported.

Hide calculation

0.9734 under ledger-default@0.3.0 at snapshot 27745 · state Supported · Review checks: 1 of 4 · stability HIGH · 5 sources, 2 independent lineages

Model ledger-default@0.3.0 (the default model, not the answer) · snapshot 27745 · trace sha256:4c9605f8b7fc8accccab83f94f8b78da04b03d7e9e75bc958d85f20545c4a3d8

Last changed at entry seq 17820; nothing logged since has borne on this claim.

How the number was reached

Each counted link is weighed by multiplying the factors the model declares; a factor it does not declare is not shown. Every factor name below links to what that number means.

Link	Working	Weight	Counted as
bc6d1413 support	relevance DIRECT 2.0 × observation MODEL_OUTPUT 0.0 × interpretation 0 steps, 1 − 0.15 × 0 1.000000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1	0.000000	0.000000 (dependent strongest only, kept d992be8a)
b2a0ebe9 support	relevance DIRECT 2.0 × observation DIRECT_TEXT 0.9 × interpretation 0 steps, 1 − 0.15 × 0 1.000000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1	1.800000	1.800000
47090d0b support	relevance DIRECT 2.0 × observation MODEL_OUTPUT 0.0 × interpretation 0 steps, 1 − 0.15 × 0 1.000000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1	0.000000	0.000000 (dependent strongest only, kept b2a0ebe9)
3029c4b4 support	relevance DIRECT 2.0 × observation MODEL_OUTPUT 0.0 × interpretation 0 steps, 1 − 0.15 × 0 1.000000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1	0.000000	0.000000 (dependent strongest only, kept b2a0ebe9)
d992be8a support	relevance DIRECT 2.0 × observation DIRECT_TEXT 0.9 × interpretation 0 steps, 1 − 0.15 × 0 1.000000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1	1.800000	1.800000

prior 0.50 → log-odds 0.000000 + 3.600000 (the counted weights) = 3.600000 → probability 0.9734

Under neighbouring settings of the same model: 0.9255 to 0.9908, a spread of 0.0653.

Half-even rounding, six places for weights and four for the probability. The same inputs under the same model reproduce this exactly; that is what the trace hash above is for. How a score is worked out explains every factor, why it is there, and what the model sets it to.

Your view

Registered views

Nobody has registered a view yet.

Registered views are personal belief, not evidence: they never change Galedra's assessment. Affiliations are self-declared and shown only for groups of 5 or more.

Checked as part of

Statements this claim was broken out of. The claim is scored on its own; a statement's reading only counts its claims.

“Embedding a well-log-based sweet-spot index as a geological prior in an attention-gated KG-SE-ResNet18 model improved reservoir-type classification accuracy...” · 1 claim · 29 September 2026
“Embedding a well-log-based sweet-spot index as a geological prior in an attention-gated KG-SE-ResNet18 model improved reservoir-type classification accuracy...” · 1 claim · 29 September 2026
“A geological-prior-guided attention network improved tight-sandstone permeability prediction and reservoir-type classification in a 12-well case study in...” · 2 claims · 29 September 2026

Evidence for

The study reports classification improvement from 86.95% to 89.28% after embedding the geological prior.

From An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks: a case study of the X Block, Chang 8 member, Jiyuan oilfield Read 2026-09-29 Relevance DIRECT Steps 0 Counted
The passage directly reports the geological prior and accuracy improvement from 86.95% to 89.28%.

From An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks: a case study of the X Block, Chang 8 member, Jiyuan oilfield Read 2026-09-29 Relevance DIRECT Steps 0 Counted
The indexed Matilda record reproduces the geological-prior mechanism and accuracy increase from 86.95% to 89.28%.

From An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks Read 2026-09-29 Relevance DIRECT Steps 0 Counted
The indexed Matilda record reproduces the geological-prior mechanism and accuracy increase.

From An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks Read 2026-09-29 Relevance DIRECT Steps 0 Counted

Independent indexed record corroborates the primary article.
The primary Scientific Reports study directly reports the geological-prior attention model and its 86.95%-to-89.28% classification improvement.

From An integrated method for permeability prediction and fluid identification in tight sandstone reservoirs using geological-prior-guided attention networks Read 2026-09-29 Relevance DIRECT Steps 0 Counted

Primary peer-reviewed petroleum-geology and machine-learning study; distinct reservoir-evaluation topic.

Evidence against

None.

Qualifications

None.

Suppressed as dependent

Evidence	Group	Kept instead
5c8435a5		d992be8a
be2fc2b9		b2a0ebe9
8bb41d5b		b2a0ebe9

Inferences

Concluded from

None.

Used as a premise in

None.

An inference is interpretation, not evidence: it never changes the assessment of its conclusion. Each premise is a claim with its own evidence.

Threads

None. Threads are for disagreements about how a determination was made — a statement whose figures are not in the passage it rests on, two sources that may share an origin. Something about the world belongs in the evidence above.

Claim edges

None. Edges are stored and displayed; v0.1 does not propagate probability across them.

Review checklist

Review checks: 1 of 4

3 checks by this claim's own author, alongside the independent review above. 1 OPPOSING EVIDENCE SEARCH · 1 QUALIFIER CHECK · 1 EVIDENCE VERIFICATION. A check by the person who recorded a claim does not raise its review coverage.

Check	Done	By
qualifiers reviewed	no
opposing search done	no
independence reviewed	no
primary source reviewed	yes	b2a0ebe9, 47090d0b, 3029c4b4

Summary

Supported. The main support is: The primary Scientific Reports study directly reports the geological-prior attention model and its 86.95%-to-89.28% classification improvement. 395c8b60

3 further items repeat the same origin and are not independent evidence. 5c8435a5be2fc2b98bb41d5b

A search for evidence in the opposing direction found something; see the counted evidence. 0a8d8a6d

Review checks: 1 of 4. coverage:ea80e47e-f54e-8d61-9f24-378fb9a2d99e

Generated by stub-v0.1; every sentence cites graph ids.

Contribution history

seq	event	detail
17506	APPENDED
17507	ACCEPT	AUTOMATIC_AFTER_VALIDATION
17516	LINK_EVIDENCE	by 1efd24fe (accepted)
17525	TASK_RESULT	by 1efd24fe (accepted)
17530	TASK_RESULT	by 1efd24fe (accepted)
17546	LINK_EVIDENCE	by 1efd24fe (accepted)
17819	LINK_EVIDENCE	by 1efd24fe (accepted)

Score trace

{
  "claim": "ea80e47e-f54e-8d61-9f24-378fb9a2d99e",
  "links": [
    {
      "kept": "fde86ac3-648b-856f-a550-47fad992be8a",
      "link": "4e675c50-228f-8c4f-8e2d-180fbc6d1413",
      "group": null,
      "reason": "dependent_strongest_only",
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "29621677-e27d-83d0-a9fb-d72e5c8435a5",
      "direction": "SUPPORT",
      "magnitude": "0.000000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "MODEL_OUTPUT",
      "source_type": "SECONDARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 0
    },
    {
      "link": "958700e3-12d4-8656-b629-6001b2a0ebe9",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "cfa4c70a-c16d-8f9e-9754-621d395c8b60",
      "direction": "SUPPORT",
      "magnitude": "1.800000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "DIRECT_TEXT",
      "source_type": "PRIMARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "1.800000",
      "interpretive_steps": 0
    },
    {
      "kept": "958700e3-12d4-8656-b629-6001b2a0ebe9",
      "link": "d68a5477-d9b2-8455-9c67-f20647090d0b",
      "group": null,
      "reason": "dependent_strongest_only",
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "835b5e50-a7c2-8552-b8da-c4febe2fc2b9",
      "direction": "SUPPORT",
      "magnitude": "0.000000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "MODEL_OUTPUT",
      "source_type": "PRIMARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 0
    },
    {
      "kept": "958700e3-12d4-8656-b629-6001b2a0ebe9",
      "link": "e9dd9426-8553-8b45-8719-9c223029c4b4",
      "group": null,
      "reason": "dependent_strongest_only",
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "d9f045af-0c48-8d3f-851c-e9598bb41d5b",
      "direction": "SUPPORT",
      "magnitude": "0.000000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "MODEL_OUTPUT",
      "source_type": "PRIMARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 0
    },
    {
      "link": "fde86ac3-648b-856f-a550-47fad992be8a",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "69e3b757-5a52-85d9-a230-b276423f456d",
      "direction": "SUPPORT",
      "magnitude": "1.800000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "DIRECT_TEXT",
      "source_type": "SECONDARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "1.800000",
      "interpretive_steps": 0
    }
  ],
  "model": "ledger-default@0.3.0",
  "prior": "0.50",
  "variants": {
    "spread": "0.0653",
    "permissive": "0.9908",
    "conservative": "0.9255"
  },
  "code_hash": "sha256:c61a6fdf35a754a0d7e958df149036a083c0eaeb7d2d2e52704ec32b0c36def7",
  "contested": false,
  "stability": "HIGH",
  "claim_type": "QUANTITATIVE",
  "config_hash": "sha256:86768038080b8ab5233f1e4b7aba10af05b5bb44caa432095150b90e81209809",
  "probability": "0.9734",
  "provisional": true,
  "evidence_sum": "3.600000",
  "snapshot_seq": 17820,
  "prior_log_odds": "0.000000",
  "support_groups": 2,
  "model_dependent": false,
  "review_coverage": "0.25",
  "truth_evaluable": true,
  "assessment_state": "SUPPORTED",
  "review_checklist": {
    "qualifiers_reviewed": {
      "by": [],
      "ok": false
    },
    "opposing_search_done": {
      "by": [],
      "ok": false
    },
    "independence_reviewed": {
      "by": [],
      "ok": false
    },
    "primary_source_reviewed": {
      "by": [
        "958700e3-12d4-8656-b629-6001b2a0ebe9",
        "d68a5477-d9b2-8455-9c67-f20647090d0b",
        "e9dd9426-8553-8b45-8719-9c223029c4b4"
      ],
      "ok": true
    }
  },
  "contradict_groups": 0,
  "rounding_boundary": false,
  "posterior_log_odds": "3.600000",
  "not_applicable_reason": null,
  "independence_unreviewed": 5
}