{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VRRJWUVO2RXTMYXQCBB6INCX4R","short_pith_number":"pith:VRRJWUVO","canonical_record":{"source":{"id":"2411.14794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T08:33:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e659e872010cf379d0ea481c3916ba941a0ed486abd8dd52eab727e27f21369d","abstract_canon_sha256":"c9d2dc81443e28def9728a53a741316d73d7c43e42903ef58d2f3028b632667e"},"schema_version":"1.0"},"canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","source":{"kind":"arxiv","id":"2411.14794","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14794","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14794v1","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14794","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"VRRJWUVO2RXT","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"VRRJWUVO2RXTMYXQ","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"VRRJWUVO","created_at":"2026-07-05T09:39:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VRRJWUVO2RXTMYXQCBB6INCX4R","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T08:33:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e659e872010cf379d0ea481c3916ba941a0ed486abd8dd52eab727e27f21369d","abstract_canon_sha256":"c9d2dc81443e28def9728a53a741316d73d7c43e42903ef58d2f3028b632667e"},"schema_version":"1.0"},"canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:12.000518Z","signature_b64":"uBDlXGCjr5R/+Vg6ORs4lbwoViINUlsC/0VURSmmqIz5JC07TRE1DUNPMbw8yuKg9WEg96j2WuiWNFeW0Ip6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","last_reissued_at":"2026-07-05T09:39:12.000063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:12.000063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14794","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":"2026-07-05T09:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkbeIM0dOSCEQ7E03aIS4v7a0lTHleL5sKW5xa+k1lMtBFrevKreUf8Zw9nWMWceuysCxcCxNK2arh46EycRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:25:58.545730Z"},"content_sha256":"f02b904a0582081c24ced631927b19af0559b63d9c8e4dc2029389c61c08a6de","schema_version":"1.0","event_id":"sha256:f02b904a0582081c24ced631927b19af0559b63d9c8e4dc2029389c61c08a6de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VRRJWUVO2RXTMYXQCBB6INCX4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hairong Shi, Le Zhuo, Shifeng Zhang, Si Liu, Songhao Han, Wei Huang, Xiaojuan Qi, Xiu Su, Xu Zhou, Yue Liao","submitted_at":"2024-11-22T08:33:36Z","abstract_excerpt":"The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14794","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/2411.14794/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":"2026-07-05T09:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRfICVALdZxA/cBMjP1Pp4csqfhEffLjs24JQotzJR9lh7EVenHVRi7pXpl9H+p17IDycgujXl8V2s38gyn8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:25:58.546730Z"},"content_sha256":"1f6e733c48508601ed249b78f21fb385d8115a5c0b141429a0c3e16574d13af2","schema_version":"1.0","event_id":"sha256:1f6e733c48508601ed249b78f21fb385d8115a5c0b141429a0c3e16574d13af2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/bundle.json","state_url":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/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":"2026-08-07T09:25:58Z","links":{"resolver":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R","bundle":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/bundle.json","state":"https://pith.science/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VRRJWUVO2RXTMYXQCBB6INCX4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VRRJWUVO2RXTMYXQCBB6INCX4R","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":"c9d2dc81443e28def9728a53a741316d73d7c43e42903ef58d2f3028b632667e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T08:33:36Z","title_canon_sha256":"e659e872010cf379d0ea481c3916ba941a0ed486abd8dd52eab727e27f21369d"},"schema_version":"1.0","source":{"id":"2411.14794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14794","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14794v1","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14794","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"VRRJWUVO2RXT","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"VRRJWUVO2RXTMYXQ","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"VRRJWUVO","created_at":"2026-07-05T09:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:1f6e733c48508601ed249b78f21fb385d8115a5c0b141429a0c3e16574d13af2","target":"graph","created_at":"2026-07-05T09:39:12Z","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/2411.14794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of Large Vision Language Models (LVLMs) has significantly improved multimodal understanding, yet challenges remain in video reasoning tasks due to the scarcity of high-quality, large-scale datasets. Existing video question-answering (VideoQA) datasets often rely on costly manual annotations with insufficient granularity or automatic construction methods with redundant frame-by-frame analysis, limiting their scalability and effectiveness for complex reasoning. To address these challenges, we introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essentia","authors_text":"Hairong Shi, Le Zhuo, Shifeng Zhang, Si Liu, Songhao Han, Wei Huang, Xiaojuan Qi, Xiu Su, Xu Zhou, Yue Liao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T08:33:36Z","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14794","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:f02b904a0582081c24ced631927b19af0559b63d9c8e4dc2029389c61c08a6de","target":"record","created_at":"2026-07-05T09:39:12Z","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":"c9d2dc81443e28def9728a53a741316d73d7c43e42903ef58d2f3028b632667e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T08:33:36Z","title_canon_sha256":"e659e872010cf379d0ea481c3916ba941a0ed486abd8dd52eab727e27f21369d"},"schema_version":"1.0","source":{"id":"2411.14794","kind":"arxiv","version":1}},"canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac629b52aed46f3662f01043e43457e45ac8c41644632dc1b9d1db4e2cc4e478","first_computed_at":"2026-07-05T09:39:12.000063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:12.000063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uBDlXGCjr5R/+Vg6ORs4lbwoViINUlsC/0VURSmmqIz5JC07TRE1DUNPMbw8yuKg9WEg96j2WuiWNFeW0Ip6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:12.000518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f02b904a0582081c24ced631927b19af0559b63d9c8e4dc2029389c61c08a6de","sha256:1f6e733c48508601ed249b78f21fb385d8115a5c0b141429a0c3e16574d13af2"],"state_sha256":"4338f38355f5489535534f0870f96b6c9e361b1055e0f35aa00e14ee8fd60a95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lvgq2fQSTGVTJ+kJiCt15gLVu2DLtx5gOblj694ve2ycXmMXsHU8VIpS1aat2y2HEHaKXO/m8H1kKtR5IykMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:25:58.553488Z","bundle_sha256":"fe237f25b9ef56fc31b29c1b300d25e72bc5946261a3da024f900d72c4f00688"}}