{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GIDTFOIXBK6TILV7EEA2HL5REY","short_pith_number":"pith:GIDTFOIX","canonical_record":{"source":{"id":"2411.06872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T11:12:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae2fa320e7df0b1896c39c5978a131ee974cfa5ca46946c509eb7e66b0aea34b","abstract_canon_sha256":"5789795cc3942b82bdd474a78bc9862ee3150a5f4293e3c12eef11cf2e8ea1fd"},"schema_version":"1.0"},"canonical_sha256":"320732b9170abd342ebf2101a3afb12608bfa4e8251007f58a98c334b590f546","source":{"kind":"arxiv","id":"2411.06872","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06872","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06872v1","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06872","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"pith_short_12","alias_value":"GIDTFOIXBK6T","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"pith_short_16","alias_value":"GIDTFOIXBK6TILV7","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"pith_short_8","alias_value":"GIDTFOIX","created_at":"2026-07-05T09:33:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GIDTFOIXBK6TILV7EEA2HL5REY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T11:12:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae2fa320e7df0b1896c39c5978a131ee974cfa5ca46946c509eb7e66b0aea34b","abstract_canon_sha256":"5789795cc3942b82bdd474a78bc9862ee3150a5f4293e3c12eef11cf2e8ea1fd"},"schema_version":"1.0"},"canonical_sha256":"320732b9170abd342ebf2101a3afb12608bfa4e8251007f58a98c334b590f546","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:53.029175Z","signature_b64":"wBO7CDOgf9ZQowNw8DAykQqxtgck3lUpsfOlXCvqpFWdk6G7x5m0UIqVHqpzepc/HtQ/r5bnLA8rEeW8YomkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320732b9170abd342ebf2101a3afb12608bfa4e8251007f58a98c334b590f546","last_reissued_at":"2026-07-05T09:33:53.028149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:53.028149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06872","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":"2026-07-05T09:33:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HrLM2fDow3x6gr+5jzYzcho2+6Yll2t7drqJKSEmpGn63EsShixwG+ne9W7eyQ3yy/zd2179zGw+lvFiHA5hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:18:06.489509Z"},"content_sha256":"77fec99b6132cd55efbb9befb5d61fc8fdf6ba3a35b2bb21561aa5c2a0615f09","schema_version":"1.0","event_id":"sha256:77fec99b6132cd55efbb9befb5d61fc8fdf6ba3a35b2bb21561aa5c2a0615f09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GIDTFOIXBK6TILV7EEA2HL5REY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Modal interpretable automatic video captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antoine Hanna-Asaad, Decky Aspandi, Titus Zaharia","submitted_at":"2024-11-11T11:12:23Z","abstract_excerpt":"Video captioning aims to describe video contents using natural language format that involves understanding and interpreting scenes, actions and events that occurs simultaneously on the view. Current approaches have mainly concentrated on visual cues, often neglecting the rich information available from other important modality of audio information, including their inter-dependencies. In this work, we introduce a novel video captioning method trained with multi-modal contrastive loss that emphasizes both multi-modal integration and interpretability. Our approach is designed to capture the depen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06872","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/2411.06872/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":"2026-07-05T09:33:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7oVvoE4okzN6QBXgWBhf3PAF8/dsColvhgxTlNOpFC76rV1JpaJZnZgaPNxUSieHf9U+rAy9cW6mDMPLdcJRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:18:06.490035Z"},"content_sha256":"4f65b3ad9b88f2912055fa049ef47347582dc4826be76196b24c9dbfadd774a6","schema_version":"1.0","event_id":"sha256:4f65b3ad9b88f2912055fa049ef47347582dc4826be76196b24c9dbfadd774a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GIDTFOIXBK6TILV7EEA2HL5REY/bundle.json","state_url":"https://pith.science/pith/GIDTFOIXBK6TILV7EEA2HL5REY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GIDTFOIXBK6TILV7EEA2HL5REY/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":"2026-08-18T14:18:06Z","links":{"resolver":"https://pith.science/pith/GIDTFOIXBK6TILV7EEA2HL5REY","bundle":"https://pith.science/pith/GIDTFOIXBK6TILV7EEA2HL5REY/bundle.json","state":"https://pith.science/pith/GIDTFOIXBK6TILV7EEA2HL5REY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GIDTFOIXBK6TILV7EEA2HL5REY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GIDTFOIXBK6TILV7EEA2HL5REY","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":"5789795cc3942b82bdd474a78bc9862ee3150a5f4293e3c12eef11cf2e8ea1fd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T11:12:23Z","title_canon_sha256":"ae2fa320e7df0b1896c39c5978a131ee974cfa5ca46946c509eb7e66b0aea34b"},"schema_version":"1.0","source":{"id":"2411.06872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06872","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06872v1","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06872","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"pith_short_12","alias_value":"GIDTFOIXBK6T","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"pith_short_16","alias_value":"GIDTFOIXBK6TILV7","created_at":"2026-07-05T09:33:53Z"},{"alias_kind":"pith_short_8","alias_value":"GIDTFOIX","created_at":"2026-07-05T09:33:53Z"}],"graph_snapshots":[{"event_id":"sha256:4f65b3ad9b88f2912055fa049ef47347582dc4826be76196b24c9dbfadd774a6","target":"graph","created_at":"2026-07-05T09:33:53Z","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/2411.06872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning aims to describe video contents using natural language format that involves understanding and interpreting scenes, actions and events that occurs simultaneously on the view. Current approaches have mainly concentrated on visual cues, often neglecting the rich information available from other important modality of audio information, including their inter-dependencies. In this work, we introduce a novel video captioning method trained with multi-modal contrastive loss that emphasizes both multi-modal integration and interpretability. Our approach is designed to capture the depen","authors_text":"Antoine Hanna-Asaad, Decky Aspandi, Titus Zaharia","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T11:12:23Z","title":"Multi-Modal interpretable automatic video captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06872","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":"sha256:77fec99b6132cd55efbb9befb5d61fc8fdf6ba3a35b2bb21561aa5c2a0615f09","target":"record","created_at":"2026-07-05T09:33:53Z","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":"5789795cc3942b82bdd474a78bc9862ee3150a5f4293e3c12eef11cf2e8ea1fd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-11T11:12:23Z","title_canon_sha256":"ae2fa320e7df0b1896c39c5978a131ee974cfa5ca46946c509eb7e66b0aea34b"},"schema_version":"1.0","source":{"id":"2411.06872","kind":"arxiv","version":1}},"canonical_sha256":"320732b9170abd342ebf2101a3afb12608bfa4e8251007f58a98c334b590f546","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"320732b9170abd342ebf2101a3afb12608bfa4e8251007f58a98c334b590f546","first_computed_at":"2026-07-05T09:33:53.028149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:53.028149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wBO7CDOgf9ZQowNw8DAykQqxtgck3lUpsfOlXCvqpFWdk6G7x5m0UIqVHqpzepc/HtQ/r5bnLA8rEeW8YomkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:53.029175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77fec99b6132cd55efbb9befb5d61fc8fdf6ba3a35b2bb21561aa5c2a0615f09","sha256:4f65b3ad9b88f2912055fa049ef47347582dc4826be76196b24c9dbfadd774a6"],"state_sha256":"3cd64dca21d1cd1c50c2a1bb40d0ea188cfa141c9f423c42f9277437d4780772"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNj8eaAx6yJQsZSZSjAXGzA8lzZRcmyvhDeaRKfVZpqX37rOOlcE1FuBBJjK9aK2xmoEigFNyFkcoTdIV7l7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:18:06.496355Z","bundle_sha256":"f715fa7ff5e0744adcdb87749aa51042a3784daa35a17f4a0335929f371bf23a"}}