{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TLPF2CN2K2JEZIPIB4EZ2TJXVF","short_pith_number":"pith:TLPF2CN2","canonical_record":{"source":{"id":"2412.12833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T11:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"a62d36ce6e14d6506ceef074bd7cb1ccc3aee4e607ea12e0cbd95c839d6df5a4","abstract_canon_sha256":"7d811e93e0731e4ac957f6ff5981e79ec0632ceac73c63a18584fca5ba333d20"},"schema_version":"1.0"},"canonical_sha256":"9ade5d09ba56924ca1e80f099d4d37a95a86ba09f47f1c528f87487f025f56e4","source":{"kind":"arxiv","id":"2412.12833","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12833","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12833v2","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12833","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"TLPF2CN2K2JE","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"TLPF2CN2K2JEZIPI","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"TLPF2CN2","created_at":"2026-07-05T11:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TLPF2CN2K2JEZIPIB4EZ2TJXVF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T11:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"a62d36ce6e14d6506ceef074bd7cb1ccc3aee4e607ea12e0cbd95c839d6df5a4","abstract_canon_sha256":"7d811e93e0731e4ac957f6ff5981e79ec0632ceac73c63a18584fca5ba333d20"},"schema_version":"1.0"},"canonical_sha256":"9ade5d09ba56924ca1e80f099d4d37a95a86ba09f47f1c528f87487f025f56e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:49.575131Z","signature_b64":"mgHn7/2euOO2HPYc3i6oxMxvds3GuiQQLnMVsPS836NHS5ZhzgkmIWeNMhI/YazCsD2y2gKDF8aYQqqit7rQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ade5d09ba56924ca1e80f099d4d37a95a86ba09f47f1c528f87487f025f56e4","last_reissued_at":"2026-07-05T11:10:49.574593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:49.574593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12833","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AChXnyxRuPafJ10yAMKjEGwV4Ly2Zx8dRlxWPvvx3VbzxVNKX23TMQlNK9maZTYxzlcZEb6o4+fTx9yXb1FoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:40:37.613820Z"},"content_sha256":"f9314b7159bc44acecde02da78abd5bb29dd4c7f9d82833300b92b7562dc94f3","schema_version":"1.0","event_id":"sha256:f9314b7159bc44acecde02da78abd5bb29dd4c7f9d82833300b92b7562dc94f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TLPF2CN2K2JEZIPIB4EZ2TJXVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rendong Wang, Zheng Cheng, Zhicheng Wang","submitted_at":"2024-12-17T11:54:47Z","abstract_excerpt":"Recently, multi-modal large language models have made significant progress. However, visual information lacking of guidance from the user's intention may lead to redundant computation and involve unnecessary visual noise, especially in long, untrimmed videos. To address this issue, we propose FocusChat, a text-guided multi-modal large language model (LLM) that emphasizes visual information correlated to the user's prompt. In detail, Our model first undergoes the semantic extraction module, which comprises a visual semantic branch and a text semantic branch to extract image and text semantics, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12833","kind":"arxiv","version":2},"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/2412.12833/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJr8Cq5TwaAT3V9cMo+B1EEI4RDNv6AzgJqUsXLvOMsMT4S4iM3WJB7haM1llphK1RE5WCpKGT9j9OuGieqXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T15:40:37.614196Z"},"content_sha256":"6f338f79beb4cdf3c8d0d65f1a5e6ff34ea05cd8ce246d00804825e2e2d75b1d","schema_version":"1.0","event_id":"sha256:6f338f79beb4cdf3c8d0d65f1a5e6ff34ea05cd8ce246d00804825e2e2d75b1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF/bundle.json","state_url":"https://pith.science/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-16T15:40:37Z","links":{"resolver":"https://pith.science/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF","bundle":"https://pith.science/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF/bundle.json","state":"https://pith.science/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLPF2CN2K2JEZIPIB4EZ2TJXVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TLPF2CN2K2JEZIPIB4EZ2TJXVF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7d811e93e0731e4ac957f6ff5981e79ec0632ceac73c63a18584fca5ba333d20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T11:54:47Z","title_canon_sha256":"a62d36ce6e14d6506ceef074bd7cb1ccc3aee4e607ea12e0cbd95c839d6df5a4"},"schema_version":"1.0","source":{"id":"2412.12833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12833","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12833v2","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12833","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"TLPF2CN2K2JE","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"TLPF2CN2K2JEZIPI","created_at":"2026-07-05T11:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"TLPF2CN2","created_at":"2026-07-05T11:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:6f338f79beb4cdf3c8d0d65f1a5e6ff34ea05cd8ce246d00804825e2e2d75b1d","target":"graph","created_at":"2026-07-05T11:10:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.12833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, multi-modal large language models have made significant progress. However, visual information lacking of guidance from the user's intention may lead to redundant computation and involve unnecessary visual noise, especially in long, untrimmed videos. To address this issue, we propose FocusChat, a text-guided multi-modal large language model (LLM) that emphasizes visual information correlated to the user's prompt. In detail, Our model first undergoes the semantic extraction module, which comprises a visual semantic branch and a text semantic branch to extract image and text semantics, ","authors_text":"Rendong Wang, Zheng Cheng, Zhicheng Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T11:54:47Z","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12833","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f9314b7159bc44acecde02da78abd5bb29dd4c7f9d82833300b92b7562dc94f3","target":"record","created_at":"2026-07-05T11:10:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7d811e93e0731e4ac957f6ff5981e79ec0632ceac73c63a18584fca5ba333d20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T11:54:47Z","title_canon_sha256":"a62d36ce6e14d6506ceef074bd7cb1ccc3aee4e607ea12e0cbd95c839d6df5a4"},"schema_version":"1.0","source":{"id":"2412.12833","kind":"arxiv","version":2}},"canonical_sha256":"9ade5d09ba56924ca1e80f099d4d37a95a86ba09f47f1c528f87487f025f56e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ade5d09ba56924ca1e80f099d4d37a95a86ba09f47f1c528f87487f025f56e4","first_computed_at":"2026-07-05T11:10:49.574593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:49.574593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mgHn7/2euOO2HPYc3i6oxMxvds3GuiQQLnMVsPS836NHS5ZhzgkmIWeNMhI/YazCsD2y2gKDF8aYQqqit7rQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:49.575131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9314b7159bc44acecde02da78abd5bb29dd4c7f9d82833300b92b7562dc94f3","sha256:6f338f79beb4cdf3c8d0d65f1a5e6ff34ea05cd8ce246d00804825e2e2d75b1d"],"state_sha256":"c3f14843e967be2f23c12ffbfb16ec5cf226230297abdb095be5526c178afac6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9aP33yteU2XuP+NKidE4W1Ee7AvAGfDXuYiGG00voT17Mk15clekmJlTjmApPWwyZM6faumC96/3ghAxxHhYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T15:40:37.616665Z","bundle_sha256":"807ee298efad5b0a190f50a1da121736305966c3b4f8d8e974b9f7f85fdc5bbc"}}