{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SX5QEMSKQNDGC3FV4DY6ZAQSVS","short_pith_number":"pith:SX5QEMSK","canonical_record":{"source":{"id":"2502.16427","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T03:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"93ea56cab7b4432dcbc0e8c8c79865213d58711f4b6217f7a09a1259adbb8c0a","abstract_canon_sha256":"d0e442a25e2fd64193dbc5363c66a0463850304e086a6b74f6c32a2c331adca4"},"schema_version":"1.0"},"canonical_sha256":"95fb02324a8346616cb5e0f1ec8212acbae6d1ec2201f71994e4d2a9654c6045","source":{"kind":"arxiv","id":"2502.16427","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16427","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16427v2","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16427","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"SX5QEMSKQNDG","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"SX5QEMSKQNDGC3FV","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"SX5QEMSK","created_at":"2026-07-05T11:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SX5QEMSKQNDGC3FV4DY6ZAQSVS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.16427","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T03:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"93ea56cab7b4432dcbc0e8c8c79865213d58711f4b6217f7a09a1259adbb8c0a","abstract_canon_sha256":"d0e442a25e2fd64193dbc5363c66a0463850304e086a6b74f6c32a2c331adca4"},"schema_version":"1.0"},"canonical_sha256":"95fb02324a8346616cb5e0f1ec8212acbae6d1ec2201f71994e4d2a9654c6045","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:25.242277Z","signature_b64":"48WgDW1Y09Bb10RdFsyHwoE9RUgLv308ok3VjUL83+WYWgGFgBCe3Nwp2zQLQEZbyXWTkmsH5L77VybbXtZ/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95fb02324a8346616cb5e0f1ec8212acbae6d1ec2201f71994e4d2a9654c6045","last_reissued_at":"2026-07-05T11:32:25.241773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:25.241773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.16427","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":"2026-07-05T11:32:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQ0vVfXC0chdl9OBewAErnx8ZGYk/CxaYhVJXMMaRl3BYknw0clXJO5g4bhNxmkHMb+gooUJ3nRLow2lxoNXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:14:54.030685Z"},"content_sha256":"af2699d5c7422ba80ef89df9adb1fe30dc0d996d2a26f138dae93bf2adf72b97","schema_version":"1.0","event_id":"sha256:af2699d5c7422ba80ef89df9adb1fe30dc0d996d2a26f138dae93bf2adf72b97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SX5QEMSKQNDGC3FV4DY6ZAQSVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Sanghyeok Chu, Seonguk Seo","submitted_at":"2025-02-23T03:59:05Z","abstract_excerpt":"Recent advances in vision-language models have led to impressive progress in caption generation for images and short video clips. However, these models remain constrained by their limited temporal receptive fields, making it difficult to produce coherent and comprehensive captions for long videos. While several methods have been proposed to aggregate information across video segments, they often rely on supervised fine-tuning or incur significant computational overhead. To address these challenges, we introduce a novel framework for long video captioning based on graph consolidation. Our appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16427","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/2502.16427/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":"2026-07-05T11:32:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJAUyqlPzYHgI492AQH/+gYTfFgx4OfP+hdPaOzwdKzFW5rZyco4By2iVZk1UQTOlEfstG1NzQTElalhbsLQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:14:54.031612Z"},"content_sha256":"a1010bcfffcc2de4ab57245ba6d815c889c7a952c24b47135fd5a3c459a14aae","schema_version":"1.0","event_id":"sha256:a1010bcfffcc2de4ab57245ba6d815c889c7a952c24b47135fd5a3c459a14aae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS/bundle.json","state_url":"https://pith.science/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS/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":"2026-08-16T07:14:54Z","links":{"resolver":"https://pith.science/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS","bundle":"https://pith.science/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS/bundle.json","state":"https://pith.science/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX5QEMSKQNDGC3FV4DY6ZAQSVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SX5QEMSKQNDGC3FV4DY6ZAQSVS","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":"d0e442a25e2fd64193dbc5363c66a0463850304e086a6b74f6c32a2c331adca4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T03:59:05Z","title_canon_sha256":"93ea56cab7b4432dcbc0e8c8c79865213d58711f4b6217f7a09a1259adbb8c0a"},"schema_version":"1.0","source":{"id":"2502.16427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.16427","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.16427v2","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16427","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"pith_short_12","alias_value":"SX5QEMSKQNDG","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"SX5QEMSKQNDGC3FV","created_at":"2026-07-05T11:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"SX5QEMSK","created_at":"2026-07-05T11:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:a1010bcfffcc2de4ab57245ba6d815c889c7a952c24b47135fd5a3c459a14aae","target":"graph","created_at":"2026-07-05T11:32:25Z","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/2502.16427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in vision-language models have led to impressive progress in caption generation for images and short video clips. However, these models remain constrained by their limited temporal receptive fields, making it difficult to produce coherent and comprehensive captions for long videos. While several methods have been proposed to aggregate information across video segments, they often rely on supervised fine-tuning or incur significant computational overhead. To address these challenges, we introduce a novel framework for long video captioning based on graph consolidation. Our appro","authors_text":"Bohyung Han, Sanghyeok Chu, Seonguk Seo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T03:59:05Z","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16427","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:af2699d5c7422ba80ef89df9adb1fe30dc0d996d2a26f138dae93bf2adf72b97","target":"record","created_at":"2026-07-05T11:32:25Z","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":"d0e442a25e2fd64193dbc5363c66a0463850304e086a6b74f6c32a2c331adca4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-23T03:59:05Z","title_canon_sha256":"93ea56cab7b4432dcbc0e8c8c79865213d58711f4b6217f7a09a1259adbb8c0a"},"schema_version":"1.0","source":{"id":"2502.16427","kind":"arxiv","version":2}},"canonical_sha256":"95fb02324a8346616cb5e0f1ec8212acbae6d1ec2201f71994e4d2a9654c6045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95fb02324a8346616cb5e0f1ec8212acbae6d1ec2201f71994e4d2a9654c6045","first_computed_at":"2026-07-05T11:32:25.241773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:25.241773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"48WgDW1Y09Bb10RdFsyHwoE9RUgLv308ok3VjUL83+WYWgGFgBCe3Nwp2zQLQEZbyXWTkmsH5L77VybbXtZ/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:25.242277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.16427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af2699d5c7422ba80ef89df9adb1fe30dc0d996d2a26f138dae93bf2adf72b97","sha256:a1010bcfffcc2de4ab57245ba6d815c889c7a952c24b47135fd5a3c459a14aae"],"state_sha256":"3fe405ae444d443d224badcbc042e972131fef912472a475bcf3bd623daeb425"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jf3VHisYLweU4EbZRfNs+0OxYc+FjB3qdP6cMF3umlTVeMhDYPsy5ijJF6N20fLQGQd+/CC5QZuuAnCbA99WDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:14:54.036802Z","bundle_sha256":"df715183cf956935c66809a37bdbb2b399c3417031116f932c7e8f85fa70dc5e"}}