{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HAC757CKYWSKMISKY35HKXZJM6","short_pith_number":"pith:HAC757CK","schema_version":"1.0","canonical_sha256":"3805fefc4ac5a4a6224ac6fa755f296791d2d915570bdefedfafecbe06b3ffee","source":{"kind":"arxiv","id":"2606.06532","version":1},"attestation_state":"computed","paper":{"title":"GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhe Chi, Yadong Mu, Yang Jin","submitted_at":"2026-06-03T17:47:49Z","abstract_excerpt":"Despite significant progress in agentic long video understanding, existing methods still lack detailed motion comprehension coupled with an efficient memory architecture. In this paper, we propose GOPAgen, a novel approach that first integrates video codec into the video understanding framework via a meticulously designed motion agent trained on Groups of Pictures (GOPs) from video codec. We further develop a GOP tree reasoning algorithm, which is naturally aligned with video codec and enhances the model's ability to understand local detailed motions in videos. Additionally, we carefully desig"},"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":"2606.06532","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T17:47:49Z","cross_cats_sorted":[],"title_canon_sha256":"1b5977c5713cfe66cdb3aba15e02e1aebf940ba02c0ceae9e17d975ca6a96be9","abstract_canon_sha256":"1f643dcf4cd83696113b949d33af21aaf2f6d74f2decd71fb9451ccc8ca2ad5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T00:03:41.246113Z","signature_b64":"Y4Qim6fImyTKF2y6g2QmmpdjQhRxS/jo0q/s962K51Eo3KkwAUOGHiq2QPIeP1yy/7NS687bbPrA4ABhr1XsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3805fefc4ac5a4a6224ac6fa755f296791d2d915570bdefedfafecbe06b3ffee","last_reissued_at":"2026-06-08T00:03:41.245264Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T00:03:41.245264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhe Chi, Yadong Mu, Yang Jin","submitted_at":"2026-06-03T17:47:49Z","abstract_excerpt":"Despite significant progress in agentic long video understanding, existing methods still lack detailed motion comprehension coupled with an efficient memory architecture. In this paper, we propose GOPAgen, a novel approach that first integrates video codec into the video understanding framework via a meticulously designed motion agent trained on Groups of Pictures (GOPs) from video codec. We further develop a GOP tree reasoning algorithm, which is naturally aligned with video codec and enhances the model's ability to understand local detailed motions in videos. Additionally, we carefully desig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06532","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/2606.06532/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":"2606.06532","created_at":"2026-06-08T00:03:41.245403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06532v1","created_at":"2026-06-08T00:03:41.245403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06532","created_at":"2026-06-08T00:03:41.245403+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAC757CKYWSK","created_at":"2026-06-08T00:03:41.245403+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAC757CKYWSKMISK","created_at":"2026-06-08T00:03:41.245403+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAC757CK","created_at":"2026-06-08T00:03:41.245403+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/HAC757CKYWSKMISKY35HKXZJM6","json":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6.json","graph_json":"https://pith.science/api/pith-number/HAC757CKYWSKMISKY35HKXZJM6/graph.json","events_json":"https://pith.science/api/pith-number/HAC757CKYWSKMISKY35HKXZJM6/events.json","paper":"https://pith.science/paper/HAC757CK"},"agent_actions":{"view_html":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6","download_json":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6.json","view_paper":"https://pith.science/paper/HAC757CK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06532&json=true","fetch_graph":"https://pith.science/api/pith-number/HAC757CKYWSKMISKY35HKXZJM6/graph.json","fetch_events":"https://pith.science/api/pith-number/HAC757CKYWSKMISKY35HKXZJM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6/action/storage_attestation","attest_author":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6/action/author_attestation","sign_citation":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6/action/citation_signature","submit_replication":"https://pith.science/pith/HAC757CKYWSKMISKY35HKXZJM6/action/replication_record"}},"created_at":"2026-06-08T00:03:41.245403+00:00","updated_at":"2026-06-08T00:03:41.245403+00:00"}