{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KFXPFXJAL354ERZIGEWEUXXSCF","short_pith_number":"pith:KFXPFXJA","schema_version":"1.0","canonical_sha256":"516ef2dd205efbc24728312c4a5ef21147dc8928a2d3574e4852ae2de6efa190","source":{"kind":"arxiv","id":"2605.16481","version":1},"attestation_state":"computed","paper":{"title":"Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aiden Yiliu Li, Anthony Steed, Nels Numan","submitted_at":"2026-05-15T17:44:53Z","abstract_excerpt":"Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in recoverable observations rather than compressed latent state alone. We propose Visual Agentic Memory (VAM), a training-free framework with three components. Online Indexing supports selective evidence retention under streaming constraints. Hierarchical Memory organises retained evidence in a Parallel Representation that aligns temporal context with spatial observations. Agentic Ret"},"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":"2605.16481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T17:44:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d86e75f25bbbf44459111cb26b98eebd3d52c014158e7ecadaddeb716ed288b","abstract_canon_sha256":"636fe3589b583fcdf6d8a3d47c8b6825690423f63cb937cd110460dd489407cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:24.279816Z","signature_b64":"L5+jZtTA1uWg3OlHaJu0TFKbphjxpeEv9iPG7CaOaiDtshSdynjWBsE2CTIyZoaWZLFD9TRPW9kstWh1yjQSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"516ef2dd205efbc24728312c4a5ef21147dc8928a2d3574e4852ae2de6efa190","last_reissued_at":"2026-05-20T00:02:24.279005Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:24.279005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aiden Yiliu Li, Anthony Steed, Nels Numan","submitted_at":"2026-05-15T17:44:53Z","abstract_excerpt":"Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in recoverable observations rather than compressed latent state alone. We propose Visual Agentic Memory (VAM), a training-free framework with three components. Online Indexing supports selective evidence retention under streaming constraints. Hierarchical Memory organises retained evidence in a Parallel Representation that aligns temporal context with spatial observations. Agentic Ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16481","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/2605.16481/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:23.110236Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.033443Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f382ddb89d6173aeebd1ca4ef3d68954a010523eeb46c28e2bf23ae26203340a"},"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":"2605.16481","created_at":"2026-05-20T00:02:24.279128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16481v1","created_at":"2026-05-20T00:02:24.279128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16481","created_at":"2026-05-20T00:02:24.279128+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFXPFXJAL354","created_at":"2026-05-20T00:02:24.279128+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFXPFXJAL354ERZI","created_at":"2026-05-20T00:02:24.279128+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFXPFXJA","created_at":"2026-05-20T00:02:24.279128+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/KFXPFXJAL354ERZIGEWEUXXSCF","json":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF.json","graph_json":"https://pith.science/api/pith-number/KFXPFXJAL354ERZIGEWEUXXSCF/graph.json","events_json":"https://pith.science/api/pith-number/KFXPFXJAL354ERZIGEWEUXXSCF/events.json","paper":"https://pith.science/paper/KFXPFXJA"},"agent_actions":{"view_html":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF","download_json":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF.json","view_paper":"https://pith.science/paper/KFXPFXJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16481&json=true","fetch_graph":"https://pith.science/api/pith-number/KFXPFXJAL354ERZIGEWEUXXSCF/graph.json","fetch_events":"https://pith.science/api/pith-number/KFXPFXJAL354ERZIGEWEUXXSCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF/action/storage_attestation","attest_author":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF/action/author_attestation","sign_citation":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF/action/citation_signature","submit_replication":"https://pith.science/pith/KFXPFXJAL354ERZIGEWEUXXSCF/action/replication_record"}},"created_at":"2026-05-20T00:02:24.279128+00:00","updated_at":"2026-05-20T00:02:24.279128+00:00"}