{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SABE7GBGY7ELGBZAVG4CAC6OTI","short_pith_number":"pith:SABE7GBG","canonical_record":{"source":{"id":"2412.10720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T07:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"063f39fbc40ece2682d02c76719c493a8f2dde70a6956f29bae8977cdce65b30","abstract_canon_sha256":"a8552f831037d08ed6507a4b42aa58c7cccc5d0c8fc42d27565c18f9672464b6"},"schema_version":"1.0"},"canonical_sha256":"90024f9826c7c8b30720a9b8200bce9a38c42a48dc126ab46dfc8193133ea004","source":{"kind":"arxiv","id":"2412.10720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10720","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10720v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10720","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"SABE7GBGY7EL","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"SABE7GBGY7ELGBZA","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"SABE7GBG","created_at":"2026-07-05T09:49:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SABE7GBGY7ELGBZAVG4CAC6OTI","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T07:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"063f39fbc40ece2682d02c76719c493a8f2dde70a6956f29bae8977cdce65b30","abstract_canon_sha256":"a8552f831037d08ed6507a4b42aa58c7cccc5d0c8fc42d27565c18f9672464b6"},"schema_version":"1.0"},"canonical_sha256":"90024f9826c7c8b30720a9b8200bce9a38c42a48dc126ab46dfc8193133ea004","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.402975Z","signature_b64":"h2gV5fmzsq1x7cGDrqgGMGw+vqKuZoUt99+1BAVdGISOc7nTHkOFU95XR5B7uw6ytVoHn8myAS8h50+f6XYHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90024f9826c7c8b30720a9b8200bce9a38c42a48dc126ab46dfc8193133ea004","last_reissued_at":"2026-07-05T09:49:20.402578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.402578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10720","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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dJfWsqw9f1vJmXxeJxjAZnp8Tq7DGON0CFJdQyRKailgFvpPz2gPZPTGwoKL3hTmRYDd/YVNnkHyl0OsSQADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:34:33.116806Z"},"content_sha256":"596826809bd05864910abe64229977e725ba73c11a10dbd4a8e303f9d3b58755","schema_version":"1.0","event_id":"sha256:596826809bd05864910abe64229977e725ba73c11a10dbd4a8e303f9d3b58755"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SABE7GBGY7ELGBZAVG4CAC6OTI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ji-jun Park, Soo-joon Choi","submitted_at":"2024-12-14T07:28:38Z","abstract_excerpt":"Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress, they often struggle to capture the causal and temporal dynamics inherent in complex video sequences. To address this limitation, we propose an enhanced framework that integrates a Causal-Temporal Reasoning Module (CTRM) into state-of-the-art LVLMs. CTRM comprises two key components: the Causal Dynamics Encoder (CDE) and the Temporal Relational Learner (TRL), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10720","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/2412.10720/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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aNHj5uos3PU/cpXlVNyOr7WBq2QdLznFP80hKqZ5xOaj2N301eKD589fFxdD2IlHXdtdqp2woeNmelTyRSeJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:34:33.117376Z"},"content_sha256":"4d0a24b2bb602c55ff89bf5283008c20a0dbe1fcded9696bbd8a90e9f450603f","schema_version":"1.0","event_id":"sha256:4d0a24b2bb602c55ff89bf5283008c20a0dbe1fcded9696bbd8a90e9f450603f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SABE7GBGY7ELGBZAVG4CAC6OTI/bundle.json","state_url":"https://pith.science/pith/SABE7GBGY7ELGBZAVG4CAC6OTI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SABE7GBGY7ELGBZAVG4CAC6OTI/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":"2026-08-19T20:34:33Z","links":{"resolver":"https://pith.science/pith/SABE7GBGY7ELGBZAVG4CAC6OTI","bundle":"https://pith.science/pith/SABE7GBGY7ELGBZAVG4CAC6OTI/bundle.json","state":"https://pith.science/pith/SABE7GBGY7ELGBZAVG4CAC6OTI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SABE7GBGY7ELGBZAVG4CAC6OTI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SABE7GBGY7ELGBZAVG4CAC6OTI","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":"a8552f831037d08ed6507a4b42aa58c7cccc5d0c8fc42d27565c18f9672464b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T07:28:38Z","title_canon_sha256":"063f39fbc40ece2682d02c76719c493a8f2dde70a6956f29bae8977cdce65b30"},"schema_version":"1.0","source":{"id":"2412.10720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10720","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10720v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10720","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"SABE7GBGY7EL","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"SABE7GBGY7ELGBZA","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"SABE7GBG","created_at":"2026-07-05T09:49:20Z"}],"graph_snapshots":[{"event_id":"sha256:4d0a24b2bb602c55ff89bf5283008c20a0dbe1fcded9696bbd8a90e9f450603f","target":"graph","created_at":"2026-07-05T09:49:20Z","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/2412.10720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress, they often struggle to capture the causal and temporal dynamics inherent in complex video sequences. To address this limitation, we propose an enhanced framework that integrates a Causal-Temporal Reasoning Module (CTRM) into state-of-the-art LVLMs. CTRM comprises two key components: the Causal Dynamics Encoder (CDE) and the Temporal Relational Learner (TRL), ","authors_text":"Ji-jun Park, Soo-joon Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T07:28:38Z","title":"Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10720","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":"sha256:596826809bd05864910abe64229977e725ba73c11a10dbd4a8e303f9d3b58755","target":"record","created_at":"2026-07-05T09:49:20Z","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":"a8552f831037d08ed6507a4b42aa58c7cccc5d0c8fc42d27565c18f9672464b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T07:28:38Z","title_canon_sha256":"063f39fbc40ece2682d02c76719c493a8f2dde70a6956f29bae8977cdce65b30"},"schema_version":"1.0","source":{"id":"2412.10720","kind":"arxiv","version":1}},"canonical_sha256":"90024f9826c7c8b30720a9b8200bce9a38c42a48dc126ab46dfc8193133ea004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90024f9826c7c8b30720a9b8200bce9a38c42a48dc126ab46dfc8193133ea004","first_computed_at":"2026-07-05T09:49:20.402578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:20.402578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h2gV5fmzsq1x7cGDrqgGMGw+vqKuZoUt99+1BAVdGISOc7nTHkOFU95XR5B7uw6ytVoHn8myAS8h50+f6XYHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:20.402975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:596826809bd05864910abe64229977e725ba73c11a10dbd4a8e303f9d3b58755","sha256:4d0a24b2bb602c55ff89bf5283008c20a0dbe1fcded9696bbd8a90e9f450603f"],"state_sha256":"f7f54bed0af262f2adb152ff7bf081a1ec0871c7fb34e48626ed8b89d84d73a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ri5GGC2OAqMi4O0fKEr8RkJCo1lR7MbbWcQXnQ+vIEs9fNo/RoZz45Ci8aYcGaIHTAsYHUEM4x4VHakX0H7GDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:34:33.124065Z","bundle_sha256":"e6f70577cf2708d6da2df64a3609cc3307bffd3fd2a6426b429e207affa3fd28"}}