{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3YJOZ3I4GQHXJEYRYZOOLH4QZP","short_pith_number":"pith:3YJOZ3I4","schema_version":"1.0","canonical_sha256":"de12eced1c340f749311c65ce59f90cbe6cdd52c2d0eb975357be1ceda818782","source":{"kind":"arxiv","id":"2606.01053","version":1},"attestation_state":"computed","paper":{"title":"AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Tian, Caixue He, Jiemin Wu, Jingying Wang, Wenshuo Chen, Yutao Yue, Zexi Li","submitted_at":"2026-05-31T06:48:43Z","abstract_excerpt":"Editing complex, long-form knowledge in Large Language Models remains a significant challenge due to the difficulty of maintaining generation coherence. Existing autoregressive methods like AnyEdit alleviate length constraints but rely on Fixed-window Chunking, which disregards logical structure and compromises consistency. To address this, we present AnyEdit++, a structure-aware framework incorporating Bayes-Chunk, an adaptive segmentation mechanism that dynamically identifies semantic boundaries based on Bayesian Surprise. We underpin this approach with a theoretical framework establishing t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T06:48:43Z","cross_cats_sorted":[],"title_canon_sha256":"10f7296d3799550ed24b58c9d0db12ad6c0bdad592aaafe14d7d8955e5a67456","abstract_canon_sha256":"0ef16b9022d450a7af3402df08d8c420e5754cb06fbb6b6fd2f5a90ffe6d27da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:19.867449Z","signature_b64":"n4e1DPJK2cUmek5xJgs+nEiOHDhi/2of7m0exPSdlPdkHdnhGe61iaiHRRXpqVlXs9S4WBH5tzNu63ApY1ceCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de12eced1c340f749311c65ce59f90cbe6cdd52c2d0eb975357be1ceda818782","last_reissued_at":"2026-06-02T01:04:19.867034Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:19.867034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Tian, Caixue He, Jiemin Wu, Jingying Wang, Wenshuo Chen, Yutao Yue, Zexi Li","submitted_at":"2026-05-31T06:48:43Z","abstract_excerpt":"Editing complex, long-form knowledge in Large Language Models remains a significant challenge due to the difficulty of maintaining generation coherence. Existing autoregressive methods like AnyEdit alleviate length constraints but rely on Fixed-window Chunking, which disregards logical structure and compromises consistency. To address this, we present AnyEdit++, a structure-aware framework incorporating Bayes-Chunk, an adaptive segmentation mechanism that dynamically identifies semantic boundaries based on Bayesian Surprise. We underpin this approach with a theoretical framework establishing t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01053","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01053/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01053","created_at":"2026-06-02T01:04:19.867092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01053v1","created_at":"2026-06-02T01:04:19.867092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01053","created_at":"2026-06-02T01:04:19.867092+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YJOZ3I4GQHX","created_at":"2026-06-02T01:04:19.867092+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YJOZ3I4GQHXJEYR","created_at":"2026-06-02T01:04:19.867092+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YJOZ3I4","created_at":"2026-06-02T01:04:19.867092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP","json":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP.json","graph_json":"https://pith.science/api/pith-number/3YJOZ3I4GQHXJEYRYZOOLH4QZP/graph.json","events_json":"https://pith.science/api/pith-number/3YJOZ3I4GQHXJEYRYZOOLH4QZP/events.json","paper":"https://pith.science/paper/3YJOZ3I4"},"agent_actions":{"view_html":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP","download_json":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP.json","view_paper":"https://pith.science/paper/3YJOZ3I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01053&json=true","fetch_graph":"https://pith.science/api/pith-number/3YJOZ3I4GQHXJEYRYZOOLH4QZP/graph.json","fetch_events":"https://pith.science/api/pith-number/3YJOZ3I4GQHXJEYRYZOOLH4QZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP/action/storage_attestation","attest_author":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP/action/author_attestation","sign_citation":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP/action/citation_signature","submit_replication":"https://pith.science/pith/3YJOZ3I4GQHXJEYRYZOOLH4QZP/action/replication_record"}},"created_at":"2026-06-02T01:04:19.867092+00:00","updated_at":"2026-06-02T01:04:19.867092+00:00"}