{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NNYZSGV57TR4ACLXNFCSAOKC5Z","short_pith_number":"pith:NNYZSGV5","schema_version":"1.0","canonical_sha256":"6b71991abdfce3c009776945203942ee470b0a683b32b9186bc694fc94757ebb","source":{"kind":"arxiv","id":"2606.05917","version":1},"attestation_state":"computed","paper":{"title":"MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gang Li, Ge Yu, Maosong Sun, Pengcheng Huang, Qing Yang, Xinze Li, Yu Gu, Yukun Yan, Zhenghao Liu","submitted_at":"2026-06-04T09:23:31Z","abstract_excerpt":"Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy video contexts. Existing frame-centric approaches improve efficiency through uniform sampling, query-aware frame selection, visual-token compression, and adaptive resolution strategies. However, they still rely on isolated and fragmented frames as the fundamental evidence units, limiting VLMs' ability to effectively capture coherent event-level semantics. To address this limitation, we propose MemoryCard, a video-me"},"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":"2606.05917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T09:23:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2e8559fa037b40dd8da762f61c2b592d8e257f8e5c9ed3f159b4ee94e9993268","abstract_canon_sha256":"0aefb71e3d1d686736b1428e914a5c47b106a82578e5626804cdb636ec2adeeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:27.461466Z","signature_b64":"Gj6m/mMXdVSSdOteBVHhKuHAv3SlLabB7HfJgFBpUfk3O1//JV/tq/9x6zn6kqHhlwwTK29L2GL8C+1dhzGWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b71991abdfce3c009776945203942ee470b0a683b32b9186bc694fc94757ebb","last_reissued_at":"2026-06-05T01:15:27.461047Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:27.461047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Gang Li, Ge Yu, Maosong Sun, Pengcheng Huang, Qing Yang, Xinze Li, Yu Gu, Yukun Yan, Zhenghao Liu","submitted_at":"2026-06-04T09:23:31Z","abstract_excerpt":"Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy video contexts. Existing frame-centric approaches improve efficiency through uniform sampling, query-aware frame selection, visual-token compression, and adaptive resolution strategies. However, they still rely on isolated and fragmented frames as the fundamental evidence units, limiting VLMs' ability to effectively capture coherent event-level semantics. To address this limitation, we propose MemoryCard, a video-me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05917","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/2606.05917/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":"2606.05917","created_at":"2026-06-05T01:15:27.461112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05917v1","created_at":"2026-06-05T01:15:27.461112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05917","created_at":"2026-06-05T01:15:27.461112+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNYZSGV57TR4","created_at":"2026-06-05T01:15:27.461112+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNYZSGV57TR4ACLX","created_at":"2026-06-05T01:15:27.461112+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNYZSGV5","created_at":"2026-06-05T01:15:27.461112+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/NNYZSGV57TR4ACLXNFCSAOKC5Z","json":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z.json","graph_json":"https://pith.science/api/pith-number/NNYZSGV57TR4ACLXNFCSAOKC5Z/graph.json","events_json":"https://pith.science/api/pith-number/NNYZSGV57TR4ACLXNFCSAOKC5Z/events.json","paper":"https://pith.science/paper/NNYZSGV5"},"agent_actions":{"view_html":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z","download_json":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z.json","view_paper":"https://pith.science/paper/NNYZSGV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05917&json=true","fetch_graph":"https://pith.science/api/pith-number/NNYZSGV57TR4ACLXNFCSAOKC5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/NNYZSGV57TR4ACLXNFCSAOKC5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z/action/storage_attestation","attest_author":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z/action/author_attestation","sign_citation":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z/action/citation_signature","submit_replication":"https://pith.science/pith/NNYZSGV57TR4ACLXNFCSAOKC5Z/action/replication_record"}},"created_at":"2026-06-05T01:15:27.461112+00:00","updated_at":"2026-06-05T01:15:27.461112+00:00"}