{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A6ABCY764SQIRPAZAHMNSE5EQC","short_pith_number":"pith:A6ABCY76","schema_version":"1.0","canonical_sha256":"07801163fee4a088bc1901d8d913a4809eb3182207e8950149c9ae28e9a7275d","source":{"kind":"arxiv","id":"2607.28678","version":1},"attestation_state":"computed","paper":{"title":"ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Chang Liu, Enbo Chen, Guanjie Cheng, Naibo Wang, Xinkui Zhao, Yifan Zhang, Yueshen Xu","submitted_at":"2026-07-29T10:25:23Z","abstract_excerpt":"Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to entity confusion, error propagation, and hallucinated answers.\n  We propose ViSAGE, a multimodal agentic memory framework that constructs self-corr"},"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":"2607.28678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T10:25:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bf63593b1b29dbde9e842e1da983455ed6511daff2c5d2d1d24ab8995b9c892a","abstract_canon_sha256":"cec8a629cf3642ae0d9f8dedd13fb6387076c53fa17206354e219cebd63770c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:12:09.288376Z","signature_b64":"g+733E7g+56AvSdxcSCB9jLlEUl9H2w5nZozBDJXswCoy7Hr6PanyFcbBXpMTje/rzGOv8HZBCRVwzMSS5t3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07801163fee4a088bc1901d8d913a4809eb3182207e8950149c9ae28e9a7275d","last_reissued_at":"2026-08-03T00:12:09.285986Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:12:09.285986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Chang Liu, Enbo Chen, Guanjie Cheng, Naibo Wang, Xinkui Zhao, Yifan Zhang, Yueshen Xu","submitted_at":"2026-07-29T10:25:23Z","abstract_excerpt":"Multimodal agents operating in long-horizon environments must build and continually update multimedia memories to support entity-consistent, temporally grounded reasoning. However, existing agentic memory approaches often discard fine-grained dentity cues under aggressive compression and segment-wise processing. They also rely heavily on vector similarity retrieval, which can surface semantically related yet identity-mismatched evidence, leading to entity confusion, error propagation, and hallucinated answers.\n  We propose ViSAGE, a multimodal agentic memory framework that constructs self-corr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28678","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/2607.28678/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":"2607.28678","created_at":"2026-08-03T00:12:09.287560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28678v1","created_at":"2026-08-03T00:12:09.287560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28678","created_at":"2026-08-03T00:12:09.287560+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6ABCY764SQI","created_at":"2026-08-03T00:12:09.287560+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6ABCY764SQIRPAZ","created_at":"2026-08-03T00:12:09.287560+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6ABCY76","created_at":"2026-08-03T00:12:09.287560+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/A6ABCY764SQIRPAZAHMNSE5EQC","json":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC.json","graph_json":"https://pith.science/api/pith-number/A6ABCY764SQIRPAZAHMNSE5EQC/graph.json","events_json":"https://pith.science/api/pith-number/A6ABCY764SQIRPAZAHMNSE5EQC/events.json","paper":"https://pith.science/paper/A6ABCY76"},"agent_actions":{"view_html":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC","download_json":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC.json","view_paper":"https://pith.science/paper/A6ABCY76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28678&json=true","fetch_graph":"https://pith.science/api/pith-number/A6ABCY764SQIRPAZAHMNSE5EQC/graph.json","fetch_events":"https://pith.science/api/pith-number/A6ABCY764SQIRPAZAHMNSE5EQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC/action/storage_attestation","attest_author":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC/action/author_attestation","sign_citation":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC/action/citation_signature","submit_replication":"https://pith.science/pith/A6ABCY764SQIRPAZAHMNSE5EQC/action/replication_record"}},"created_at":"2026-08-03T00:12:09.287560+00:00","updated_at":"2026-08-03T00:12:09.287560+00:00"}