{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3PT6EIIR34WTUDW4BFTLRJH4YS","short_pith_number":"pith:3PT6EIIR","canonical_record":{"source":{"id":"2411.14505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T09:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"9b8267b50367b5baab17c52592628f97805238fbfd0cc26a26b994bafb430540","abstract_canon_sha256":"6ba0926fca204b59a08d2dd4c9b90da5c2e3fa35bb4b92b2b05adfcf61d2bb81"},"schema_version":"1.0"},"canonical_sha256":"dbe7e22111df2d3a0edc0966b8a4fcc495ddb5f1ce6e49d04816752e2dc7f9cc","source":{"kind":"arxiv","id":"2411.14505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14505","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14505v1","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14505","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"3PT6EIIR34WT","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"3PT6EIIR34WTUDW4","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"3PT6EIIR","created_at":"2026-07-05T09:38:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3PT6EIIR34WTUDW4BFTLRJH4YS","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T09:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"9b8267b50367b5baab17c52592628f97805238fbfd0cc26a26b994bafb430540","abstract_canon_sha256":"6ba0926fca204b59a08d2dd4c9b90da5c2e3fa35bb4b92b2b05adfcf61d2bb81"},"schema_version":"1.0"},"canonical_sha256":"dbe7e22111df2d3a0edc0966b8a4fcc495ddb5f1ce6e49d04816752e2dc7f9cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:52.473232Z","signature_b64":"BGVaLNplZrCEGmzLuJpE/tNxpQbi0ohJlnFpElb6gwecq8+IwbxcJNsO2g7IS3XCdGi5Hr/i1kwOKKAjEu00Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe7e22111df2d3a0edc0966b8a4fcc495ddb5f1ce6e49d04816752e2dc7f9cc","last_reissued_at":"2026-07-05T09:38:52.472809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:52.472809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14505","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJ+CYQvLsxVCLq7kOedYzvDQFNfco12W3yOxDF/3pRYqEY8Zb6c/zqToBjXgIE1J5sSJOSm6ZFMV3IiQOzkGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:32:16.944401Z"},"content_sha256":"4bae8450cfd75577be09d7e0a7007828f62b61519b7ab2c0cc737531c67f3294","schema_version":"1.0","event_id":"sha256:4bae8450cfd75577be09d7e0a7007828f62b61519b7ab2c0cc737531c67f3294"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3PT6EIIR34WTUDW4BFTLRJH4YS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An Yu, Jian Li, Ming-Ching Chang, Min Xia, Shengpeng Ji, Weiheng Lu","submitted_at":"2024-11-21T09:34:23Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction. We propose the Large Language-and-Vision Assistant for Moment Retrieval (LLaVA-MR), which enables accurate moment retrieval and contextual grounding in videos using MLLMs. LLaVA-MR combines Dense Frame and Time Encoding (DFTE) for spatial-temporal feature extraction, Informative Frame Selection (IFS) for capturing brief visual and motion patterns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14505","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/2411.14505/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":"2026-07-05T09:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SE71YbYJJ19FeALcq/LKtQIahL/OWcqFWJltm/3ag9d9Esx1BgyY+6pD2sdLENWNnihsjOOzuiI0A5EGrWxCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:32:16.945139Z"},"content_sha256":"ff99e623cacf725b2ddc25ea8beb9419fe4c6ac6f9921dbbba188d5b4e5544e0","schema_version":"1.0","event_id":"sha256:ff99e623cacf725b2ddc25ea8beb9419fe4c6ac6f9921dbbba188d5b4e5544e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3PT6EIIR34WTUDW4BFTLRJH4YS/bundle.json","state_url":"https://pith.science/pith/3PT6EIIR34WTUDW4BFTLRJH4YS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3PT6EIIR34WTUDW4BFTLRJH4YS/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":"2026-08-11T20:32:16Z","links":{"resolver":"https://pith.science/pith/3PT6EIIR34WTUDW4BFTLRJH4YS","bundle":"https://pith.science/pith/3PT6EIIR34WTUDW4BFTLRJH4YS/bundle.json","state":"https://pith.science/pith/3PT6EIIR34WTUDW4BFTLRJH4YS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3PT6EIIR34WTUDW4BFTLRJH4YS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3PT6EIIR34WTUDW4BFTLRJH4YS","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":"6ba0926fca204b59a08d2dd4c9b90da5c2e3fa35bb4b92b2b05adfcf61d2bb81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T09:34:23Z","title_canon_sha256":"9b8267b50367b5baab17c52592628f97805238fbfd0cc26a26b994bafb430540"},"schema_version":"1.0","source":{"id":"2411.14505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14505","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14505v1","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14505","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"3PT6EIIR34WT","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"3PT6EIIR34WTUDW4","created_at":"2026-07-05T09:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"3PT6EIIR","created_at":"2026-07-05T09:38:52Z"}],"graph_snapshots":[{"event_id":"sha256:ff99e623cacf725b2ddc25ea8beb9419fe4c6ac6f9921dbbba188d5b4e5544e0","target":"graph","created_at":"2026-07-05T09:38:52Z","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/2411.14505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction. We propose the Large Language-and-Vision Assistant for Moment Retrieval (LLaVA-MR), which enables accurate moment retrieval and contextual grounding in videos using MLLMs. LLaVA-MR combines Dense Frame and Time Encoding (DFTE) for spatial-temporal feature extraction, Informative Frame Selection (IFS) for capturing brief visual and motion patterns","authors_text":"An Yu, Jian Li, Ming-Ching Chang, Min Xia, Shengpeng Ji, Weiheng Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T09:34:23Z","title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14505","kind":"arxiv","version":1},"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":"sha256:4bae8450cfd75577be09d7e0a7007828f62b61519b7ab2c0cc737531c67f3294","target":"record","created_at":"2026-07-05T09:38:52Z","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":"6ba0926fca204b59a08d2dd4c9b90da5c2e3fa35bb4b92b2b05adfcf61d2bb81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T09:34:23Z","title_canon_sha256":"9b8267b50367b5baab17c52592628f97805238fbfd0cc26a26b994bafb430540"},"schema_version":"1.0","source":{"id":"2411.14505","kind":"arxiv","version":1}},"canonical_sha256":"dbe7e22111df2d3a0edc0966b8a4fcc495ddb5f1ce6e49d04816752e2dc7f9cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbe7e22111df2d3a0edc0966b8a4fcc495ddb5f1ce6e49d04816752e2dc7f9cc","first_computed_at":"2026-07-05T09:38:52.472809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:52.472809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BGVaLNplZrCEGmzLuJpE/tNxpQbi0ohJlnFpElb6gwecq8+IwbxcJNsO2g7IS3XCdGi5Hr/i1kwOKKAjEu00Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:52.473232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bae8450cfd75577be09d7e0a7007828f62b61519b7ab2c0cc737531c67f3294","sha256:ff99e623cacf725b2ddc25ea8beb9419fe4c6ac6f9921dbbba188d5b4e5544e0"],"state_sha256":"37fc3ed378833a97153b5ecffa90ab0a7538933e95d454ffde6f83319e87203d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"guwwrqVzxoWi+w60RkqKvrkSmLnIJADj9hIS1YddCJ0gm3ZysHjWehhKUGsjK6TZE/qdwQ4YrGKKjv38yCZICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:32:16.951481Z","bundle_sha256":"049f95f59f107420532035ed1bd1136bc459b1c4c3f36c2e5e54d5d570ed5ffb"}}