{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KVV6UR7DPVCLXNLHHRYJF23C7G","short_pith_number":"pith:KVV6UR7D","schema_version":"1.0","canonical_sha256":"556bea47e37d44bbb5673c7092eb62f9861e5105ff3731b30c5cbfa307839320","source":{"kind":"arxiv","id":"2608.04866","version":1},"attestation_state":"computed","paper":{"title":"Persistent Object Narratives for Token-Efficient Video Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junzhe Chen, Siyuan Meng, Xiaojie Guo","submitted_at":"2026-08-05T13:59:04Z","abstract_excerpt":"Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-intensive and provide limited explicit structure for linking recurring object evidence across time. We introduce SlotNarrative, a slot-based interface that organizes a video into persistent object narratives represented by compact object-state tokens. Rather than compressing frame-wise features before establishing temporal correspondence, SlotNarrative first groups visual features into object-like slots and then associates recurring observations wi"},"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":"2608.04866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T13:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"31c24698eb013c5bc26fff010136510f04d054df88f68e1693c1bd452384af21","abstract_canon_sha256":"06e6c399eba3b89a4920403405a9a95ab8fe05d479070247bf6d04b83a906812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:25.594945Z","signature_b64":"Ephf16qPkICQSuTzEYLMBqZtAcJm4yWaMN7LXgV+bDf5SEKRS1bSO0etBNXmqL/ZWnwY3J3RTLxEufqXRR9hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"556bea47e37d44bbb5673c7092eb62f9861e5105ff3731b30c5cbfa307839320","last_reissued_at":"2026-08-06T01:47:25.593532Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:25.593532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Persistent Object Narratives for Token-Efficient Video Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junzhe Chen, Siyuan Meng, Xiaojie Guo","submitted_at":"2026-08-05T13:59:04Z","abstract_excerpt":"Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-intensive and provide limited explicit structure for linking recurring object evidence across time. We introduce SlotNarrative, a slot-based interface that organizes a video into persistent object narratives represented by compact object-state tokens. Rather than compressing frame-wise features before establishing temporal correspondence, SlotNarrative first groups visual features into object-like slots and then associates recurring observations wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04866","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/2608.04866/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":"2608.04866","created_at":"2026-08-06T01:47:25.595364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04866v1","created_at":"2026-08-06T01:47:25.595364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04866","created_at":"2026-08-06T01:47:25.595364+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVV6UR7DPVCL","created_at":"2026-08-06T01:47:25.595364+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVV6UR7DPVCLXNLH","created_at":"2026-08-06T01:47:25.595364+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVV6UR7D","created_at":"2026-08-06T01:47:25.595364+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/KVV6UR7DPVCLXNLHHRYJF23C7G","json":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G.json","graph_json":"https://pith.science/api/pith-number/KVV6UR7DPVCLXNLHHRYJF23C7G/graph.json","events_json":"https://pith.science/api/pith-number/KVV6UR7DPVCLXNLHHRYJF23C7G/events.json","paper":"https://pith.science/paper/KVV6UR7D"},"agent_actions":{"view_html":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G","download_json":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G.json","view_paper":"https://pith.science/paper/KVV6UR7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04866&json=true","fetch_graph":"https://pith.science/api/pith-number/KVV6UR7DPVCLXNLHHRYJF23C7G/graph.json","fetch_events":"https://pith.science/api/pith-number/KVV6UR7DPVCLXNLHHRYJF23C7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G/action/storage_attestation","attest_author":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G/action/author_attestation","sign_citation":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G/action/citation_signature","submit_replication":"https://pith.science/pith/KVV6UR7DPVCLXNLHHRYJF23C7G/action/replication_record"}},"created_at":"2026-08-06T01:47:25.595364+00:00","updated_at":"2026-08-06T01:47:25.595364+00:00"}