{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KXXOCX6QDROYMPEU6EWWC4CCG2","short_pith_number":"pith:KXXOCX6Q","canonical_record":{"source":{"id":"2507.17050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T22:16:37Z","cross_cats_sorted":[],"title_canon_sha256":"a969b2e4acce21e4349e3a2c52f7e228764c79114f060ea7d425e9a96248b17e","abstract_canon_sha256":"6eb875286526ca9d1b8d9e23a10b55002cf707035942002ae351336b0071acd0"},"schema_version":"1.0"},"canonical_sha256":"55eee15fd01c5d863c94f12d6170423690f2d91f026d0e8758936a4aceb58ba8","source":{"kind":"arxiv","id":"2507.17050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17050","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17050v1","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17050","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"KXXOCX6QDROY","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"KXXOCX6QDROYMPEU","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"KXXOCX6Q","created_at":"2026-07-05T11:42:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KXXOCX6QDROYMPEU6EWWC4CCG2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.17050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T22:16:37Z","cross_cats_sorted":[],"title_canon_sha256":"a969b2e4acce21e4349e3a2c52f7e228764c79114f060ea7d425e9a96248b17e","abstract_canon_sha256":"6eb875286526ca9d1b8d9e23a10b55002cf707035942002ae351336b0071acd0"},"schema_version":"1.0"},"canonical_sha256":"55eee15fd01c5d863c94f12d6170423690f2d91f026d0e8758936a4aceb58ba8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:00.704734Z","signature_b64":"AxlR3PMAWeeYLSV8tRM+rr4soTb0oTtD/oSppdlNZJr4loT/M8r8kGM71oK7K8CjcwPK9P/nwYixlr80kUhhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55eee15fd01c5d863c94f12d6170423690f2d91f026d0e8758936a4aceb58ba8","last_reissued_at":"2026-07-05T11:42:00.704186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:00.704186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.17050","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":"2026-07-05T11:42:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwGxtL60+eYjLXMnG7pYrpjLe2UyOLeV6gtdTwS3PA7tfGjmBFhIts/d66sgHBe0VfeSE/TuTjgXM/SgqZhlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:08:31.621173Z"},"content_sha256":"84d8e431f354bddc91d60eee8b3af1931f2cec6907baf42713c10e8afaa1689b","schema_version":"1.0","event_id":"sha256:84d8e431f354bddc91d60eee8b3af1931f2cec6907baf42713c10e8afaa1689b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KXXOCX6QDROYMPEU6EWWC4CCG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anand Bodas, Sharath Nittur Sridhar, Subarna Tripathi, Tahani Trigui, Tz-Ying Wu","submitted_at":"2025-07-22T22:16:37Z","abstract_excerpt":"In this paper, we introduce VideoNarrator, a novel training-free pipeline designed to generate dense video captions that offer a structured snapshot of video content. These captions offer detailed narrations with precise timestamps, capturing the nuances present in each segment of the video. Despite advancements in multimodal large language models (MLLMs) for video comprehension, these models often struggle with temporally aligned narrations and tend to hallucinate, particularly in unfamiliar scenarios. VideoNarrator addresses these challenges by leveraging a flexible pipeline where off-the-sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17050","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/2507.17050/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":"2026-07-05T11:42:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuliKidDW2np/lIm73OZPFOJuur3T5LWF/VzL7ImWhC0xgOl5QR5nXE9b1r5RH3TYa/+53CZs+NoVkRgG/DnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:08:31.621667Z"},"content_sha256":"916dc6e7b71b9f73aef2ae470af964fe8fcee034fdc45e04df64eb3bf4564e5c","schema_version":"1.0","event_id":"sha256:916dc6e7b71b9f73aef2ae470af964fe8fcee034fdc45e04df64eb3bf4564e5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXXOCX6QDROYMPEU6EWWC4CCG2/bundle.json","state_url":"https://pith.science/pith/KXXOCX6QDROYMPEU6EWWC4CCG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXXOCX6QDROYMPEU6EWWC4CCG2/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":"2026-08-04T11:08:31Z","links":{"resolver":"https://pith.science/pith/KXXOCX6QDROYMPEU6EWWC4CCG2","bundle":"https://pith.science/pith/KXXOCX6QDROYMPEU6EWWC4CCG2/bundle.json","state":"https://pith.science/pith/KXXOCX6QDROYMPEU6EWWC4CCG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXXOCX6QDROYMPEU6EWWC4CCG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KXXOCX6QDROYMPEU6EWWC4CCG2","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":"6eb875286526ca9d1b8d9e23a10b55002cf707035942002ae351336b0071acd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T22:16:37Z","title_canon_sha256":"a969b2e4acce21e4349e3a2c52f7e228764c79114f060ea7d425e9a96248b17e"},"schema_version":"1.0","source":{"id":"2507.17050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17050","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17050v1","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17050","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"KXXOCX6QDROY","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"KXXOCX6QDROYMPEU","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"KXXOCX6Q","created_at":"2026-07-05T11:42:00Z"}],"graph_snapshots":[{"event_id":"sha256:916dc6e7b71b9f73aef2ae470af964fe8fcee034fdc45e04df64eb3bf4564e5c","target":"graph","created_at":"2026-07-05T11:42:00Z","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/2507.17050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce VideoNarrator, a novel training-free pipeline designed to generate dense video captions that offer a structured snapshot of video content. These captions offer detailed narrations with precise timestamps, capturing the nuances present in each segment of the video. Despite advancements in multimodal large language models (MLLMs) for video comprehension, these models often struggle with temporally aligned narrations and tend to hallucinate, particularly in unfamiliar scenarios. VideoNarrator addresses these challenges by leveraging a flexible pipeline where off-the-sh","authors_text":"Anand Bodas, Sharath Nittur Sridhar, Subarna Tripathi, Tahani Trigui, Tz-Ying Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T22:16:37Z","title":"Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17050","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":"sha256:84d8e431f354bddc91d60eee8b3af1931f2cec6907baf42713c10e8afaa1689b","target":"record","created_at":"2026-07-05T11:42:00Z","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":"6eb875286526ca9d1b8d9e23a10b55002cf707035942002ae351336b0071acd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T22:16:37Z","title_canon_sha256":"a969b2e4acce21e4349e3a2c52f7e228764c79114f060ea7d425e9a96248b17e"},"schema_version":"1.0","source":{"id":"2507.17050","kind":"arxiv","version":1}},"canonical_sha256":"55eee15fd01c5d863c94f12d6170423690f2d91f026d0e8758936a4aceb58ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55eee15fd01c5d863c94f12d6170423690f2d91f026d0e8758936a4aceb58ba8","first_computed_at":"2026-07-05T11:42:00.704186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:00.704186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AxlR3PMAWeeYLSV8tRM+rr4soTb0oTtD/oSppdlNZJr4loT/M8r8kGM71oK7K8CjcwPK9P/nwYixlr80kUhhAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:00.704734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84d8e431f354bddc91d60eee8b3af1931f2cec6907baf42713c10e8afaa1689b","sha256:916dc6e7b71b9f73aef2ae470af964fe8fcee034fdc45e04df64eb3bf4564e5c"],"state_sha256":"9ce52f37cfbea35d20adb6ad431f8a0d49014e20bab80a2289a1d6c9b26fedfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XBkgfbjx5/dGrZv7yjGD6GJfJqK4fKogxBFmNhhhSPoxgyHm2Kxwv/ovJD66Vld7nEqFJPxMwy42yjTVnrFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:08:31.625944Z","bundle_sha256":"4afbeb807327a19f94511179d32734f5acd28aa7b689f157d4f95b21dd243330"}}