{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PARM3F3FRZX5FHLSCXMXYK6G3S","short_pith_number":"pith:PARM3F3F","schema_version":"1.0","canonical_sha256":"7822cd97658e6fd29d7215d97c2bc6dc9011559ab4034e332fcca5c5343933ee","source":{"kind":"arxiv","id":"2606.07512","version":1},"attestation_state":"computed","paper":{"title":"MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaoyang Zhang, Chunhua Shen, Cong Chen, Guangming Yao, Guo Gan, Hao Chen, Jingdong Chen, Kaixiang Ji, Yi Yuan, Zhen Yang","submitted_at":"2026-06-05T17:59:21Z","abstract_excerpt":"Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning m"},"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":"2606.07512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T17:59:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bea48001a1071561d766301f16546a9c2e59f13eca722ab1ccbc2acf1457b755","abstract_canon_sha256":"b4bebce4fd5e68ac9b2614096cd5f021d6293612ff43c85a737066f0982f2001"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:32.048853Z","signature_b64":"QxHOS5t2zKRC015wW8Ibpt6wF+5rQjBxhp7kFAgcrfYJe2ZSetFjo36nJ5mS64fP0fM6ptKlzldHoHqIZ875DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7822cd97658e6fd29d7215d97c2bc6dc9011559ab4034e332fcca5c5343933ee","last_reissued_at":"2026-06-08T01:05:32.048055Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:32.048055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaoyang Zhang, Chunhua Shen, Cong Chen, Guangming Yao, Guo Gan, Hao Chen, Jingdong Chen, Kaixiang Ji, Yi Yuan, Zhen Yang","submitted_at":"2026-06-05T17:59:21Z","abstract_excerpt":"Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07512","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/2606.07512/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":"2606.07512","created_at":"2026-06-08T01:05:32.048185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07512v1","created_at":"2026-06-08T01:05:32.048185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07512","created_at":"2026-06-08T01:05:32.048185+00:00"},{"alias_kind":"pith_short_12","alias_value":"PARM3F3FRZX5","created_at":"2026-06-08T01:05:32.048185+00:00"},{"alias_kind":"pith_short_16","alias_value":"PARM3F3FRZX5FHLS","created_at":"2026-06-08T01:05:32.048185+00:00"},{"alias_kind":"pith_short_8","alias_value":"PARM3F3F","created_at":"2026-06-08T01:05:32.048185+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/PARM3F3FRZX5FHLSCXMXYK6G3S","json":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S.json","graph_json":"https://pith.science/api/pith-number/PARM3F3FRZX5FHLSCXMXYK6G3S/graph.json","events_json":"https://pith.science/api/pith-number/PARM3F3FRZX5FHLSCXMXYK6G3S/events.json","paper":"https://pith.science/paper/PARM3F3F"},"agent_actions":{"view_html":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S","download_json":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S.json","view_paper":"https://pith.science/paper/PARM3F3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07512&json=true","fetch_graph":"https://pith.science/api/pith-number/PARM3F3FRZX5FHLSCXMXYK6G3S/graph.json","fetch_events":"https://pith.science/api/pith-number/PARM3F3FRZX5FHLSCXMXYK6G3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S/action/storage_attestation","attest_author":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S/action/author_attestation","sign_citation":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S/action/citation_signature","submit_replication":"https://pith.science/pith/PARM3F3FRZX5FHLSCXMXYK6G3S/action/replication_record"}},"created_at":"2026-06-08T01:05:32.048185+00:00","updated_at":"2026-06-08T01:05:32.048185+00:00"}