{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6VHLBPGNCKC47OACUTX6QWGKC4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f3830e37652ce4530035b608284b0976a119d71d34708d2a32696b4ad1643ba9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T03:41:53Z","title_canon_sha256":"f1ed4b78ad624a0ab1cce7aa27de3fbcf424262528d6abed3de7da0c91b6672e"},"schema_version":"1.0","source":{"id":"2604.12243","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12243","created_at":"2026-07-02T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12243v2","created_at":"2026-07-02T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12243","created_at":"2026-07-02T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"6VHLBPGNCKC4","created_at":"2026-07-02T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"6VHLBPGNCKC47OAC","created_at":"2026-07-02T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"6VHLBPGN","created_at":"2026-07-02T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:54546fcd2682dfe824d5ada5bf45ce11dea8fb83aa629097a18f84237f4303c5","target":"graph","created_at":"2026-07-02T01:18:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CKM-Lite achieves strong predictive coverage through incremental accumulation, outperforming batch processing on hit rate (+2.8%, p=0.006), hypothesis yield (+3.6, p<0.001), best-match alignment (+0.43, p<0.001) while reducing token cost by 92%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM-based categorization of findings as novel/confirming/contradicting and conditioning on evolution trajectories accurately reflects real scientific knowledge dynamics without introducing systematic bias from the model's training data or judgment process."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Incremental sliding-window processing of evolving literature via CKM-Lite outperforms batch methods on predictive hit rate, hypothesis yield, and alignment while cutting token costs by 92%, with change-aware analysis revealing quality-coverage trade-offs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Processing scientific literature in sliding time windows with incremental updates generates better and cheaper hypotheses than batch analysis."}],"snapshot_sha256":"c1ff066e7d555810df54e1d40a77a9e1a129dedf033de63f99afd57f57817905"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.12243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research. Existing LLM-driven scientific discovery systems are typically limited to one-shot prompting on static literature snapshots and are validated only against contemporary judges such as human reviewers, agent peer review, wet-lab assays, or self-evaluation, leaving open whether they can anticipate future trends. We present Continuous Knowledge Metabolism (CKM), an AI workflow for hypothesis generation with three key capabilities: (i) continuous literature metabol","authors_text":"Jinkai Tao, Menglin Yang, Xiaoyu Liu, Yubo Wang","cross_cats":["cs.AI"],"headline":"Processing scientific literature in sliding time windows with incremental updates generates better and cheaper hypotheses than batch analysis.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T03:41:53Z","title":"Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.12243","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:23:37.071994Z","id":"3ed5dab0-f453-4207-a923-f3675f1e2e51","model_set":{"reader":"grok-4.3"},"one_line_summary":"Incremental sliding-window processing of evolving literature via CKM-Lite outperforms batch methods on predictive hit rate, hypothesis yield, and alignment while cutting token costs by 92%, with change-aware analysis revealing quality-coverage trade-offs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Processing scientific literature in sliding time windows with incremental updates generates better and cheaper hypotheses than batch analysis.","strongest_claim":"CKM-Lite achieves strong predictive coverage through incremental accumulation, outperforming batch processing on hit rate (+2.8%, p=0.006), hypothesis yield (+3.6, p<0.001), best-match alignment (+0.43, p<0.001) while reducing token cost by 92%.","weakest_assumption":"That LLM-based categorization of findings as novel/confirming/contradicting and conditioning on evolution trajectories accurately reflects real scientific knowledge dynamics without introducing systematic bias from the model's training data or judgment process."}},"verdict_id":"3ed5dab0-f453-4207-a923-f3675f1e2e51"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1bc3bd6e7c8025f2ee4a2a23dff22788bdc60d173325633dddc544072def638f","target":"record","created_at":"2026-07-02T01:18:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f3830e37652ce4530035b608284b0976a119d71d34708d2a32696b4ad1643ba9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T03:41:53Z","title_canon_sha256":"f1ed4b78ad624a0ab1cce7aa27de3fbcf424262528d6abed3de7da0c91b6672e"},"schema_version":"1.0","source":{"id":"2604.12243","kind":"arxiv","version":2}},"canonical_sha256":"f54eb0bccd1285cfb802a4efe858ca1706e15dfda2d437016766410fcc913436","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f54eb0bccd1285cfb802a4efe858ca1706e15dfda2d437016766410fcc913436","first_computed_at":"2026-07-02T01:18:08.052923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:08.052923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yUFEXHwsaVqp5GZ26JQm85S9XiI+JUZIA8qEIovC44GRNBpOa+qJInPZU4zLczTVLMdk7DTV+5r/L0hIMO8sCA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:08.053391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.12243","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bc3bd6e7c8025f2ee4a2a23dff22788bdc60d173325633dddc544072def638f","sha256:54546fcd2682dfe824d5ada5bf45ce11dea8fb83aa629097a18f84237f4303c5"],"state_sha256":"38a5abaf39872601fbb623fd6638c275839c95d875c8a6cb30696c1ed0584de9"}