{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6EZ2RMKDESYKU5INJULU3PKDYL","short_pith_number":"pith:6EZ2RMKD","canonical_record":{"source":{"id":"2507.04815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T09:33:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce355c484bc03d62e4f7bb41a6b9de294996e32e300c4e73e1b0451cdd284585","abstract_canon_sha256":"9db59cec38fec097d466d933972ae95f0b532f0438b980f564b5fabe1fe9064a"},"schema_version":"1.0"},"canonical_sha256":"f133a8b14324b0aa750d4d174dbd43c2cd9a14d0578675e032127c9814d8153c","source":{"kind":"arxiv","id":"2507.04815","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04815","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04815v1","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04815","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"pith_short_12","alias_value":"6EZ2RMKDESYK","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"pith_short_16","alias_value":"6EZ2RMKDESYKU5IN","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"pith_short_8","alias_value":"6EZ2RMKD","created_at":"2026-07-05T11:32:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6EZ2RMKDESYKU5INJULU3PKDYL","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T09:33:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce355c484bc03d62e4f7bb41a6b9de294996e32e300c4e73e1b0451cdd284585","abstract_canon_sha256":"9db59cec38fec097d466d933972ae95f0b532f0438b980f564b5fabe1fe9064a"},"schema_version":"1.0"},"canonical_sha256":"f133a8b14324b0aa750d4d174dbd43c2cd9a14d0578675e032127c9814d8153c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:54.637638Z","signature_b64":"BlTUDoRYMzvm9mYahT8BWUF4SSDOgbySKgfwpNcMpqdEPdb7ss+VAuvkqJt+sZrPHt6bX5U7H6XQ7Wp4cXRYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f133a8b14324b0aa750d4d174dbd43c2cd9a14d0578675e032127c9814d8153c","last_reissued_at":"2026-07-05T11:32:54.637120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:54.637120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04815","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":"2026-07-05T11:32:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OhdkFgCB5L9AI6ZdGO62WfaB+XRQ0uKls6O4DUQ+4oAcvaDTPEvPJ0M9t0jZYqwtTmhvtkWG5fN+eql7mbpLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:48:40.135399Z"},"content_sha256":"3fdf4ab4bad0d404f4fd288bc1820cb406d8b1327c43fac9634cad473dd7785f","schema_version":"1.0","event_id":"sha256:3fdf4ab4bad0d404f4fd288bc1820cb406d8b1327c43fac9634cad473dd7785f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6EZ2RMKDESYKU5INJULU3PKDYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Marius Leordeanu, Mihai Masala","submitted_at":"2025-07-07T09:33:19Z","abstract_excerpt":"The task of describing video content in natural language is commonly referred to as video captioning. Unlike conventional video captions, which are typically brief and widely available, long-form paragraph descriptions in natural language are scarce. This limitation of current datasets is due to the expensive human manual annotation required and to the highly challenging task of explaining the language formation process from the perspective of the underlying story, as a complex system of interconnected events in space and time. Through a thorough analysis of recently published methods and avai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04815","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/2507.04815/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":"2026-07-05T11:32:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kg87QD64fk7znqTNGc7nythrW5p1CdSV6oHaLwaZ2NotX9xT9TOYHvFCawo6RiOseo1rwyCuqKazPxsEaMlgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:48:40.136122Z"},"content_sha256":"f80d8d2210afae8bfcbafa59b24aab976ce43285710d78ac07c4d20fadfa4d5e","schema_version":"1.0","event_id":"sha256:f80d8d2210afae8bfcbafa59b24aab976ce43285710d78ac07c4d20fadfa4d5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EZ2RMKDESYKU5INJULU3PKDYL/bundle.json","state_url":"https://pith.science/pith/6EZ2RMKDESYKU5INJULU3PKDYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EZ2RMKDESYKU5INJULU3PKDYL/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":"2026-08-16T01:48:40Z","links":{"resolver":"https://pith.science/pith/6EZ2RMKDESYKU5INJULU3PKDYL","bundle":"https://pith.science/pith/6EZ2RMKDESYKU5INJULU3PKDYL/bundle.json","state":"https://pith.science/pith/6EZ2RMKDESYKU5INJULU3PKDYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EZ2RMKDESYKU5INJULU3PKDYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6EZ2RMKDESYKU5INJULU3PKDYL","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":"9db59cec38fec097d466d933972ae95f0b532f0438b980f564b5fabe1fe9064a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T09:33:19Z","title_canon_sha256":"ce355c484bc03d62e4f7bb41a6b9de294996e32e300c4e73e1b0451cdd284585"},"schema_version":"1.0","source":{"id":"2507.04815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04815","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04815v1","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04815","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"pith_short_12","alias_value":"6EZ2RMKDESYK","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"pith_short_16","alias_value":"6EZ2RMKDESYKU5IN","created_at":"2026-07-05T11:32:54Z"},{"alias_kind":"pith_short_8","alias_value":"6EZ2RMKD","created_at":"2026-07-05T11:32:54Z"}],"graph_snapshots":[{"event_id":"sha256:f80d8d2210afae8bfcbafa59b24aab976ce43285710d78ac07c4d20fadfa4d5e","target":"graph","created_at":"2026-07-05T11:32:54Z","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/2507.04815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of describing video content in natural language is commonly referred to as video captioning. Unlike conventional video captions, which are typically brief and widely available, long-form paragraph descriptions in natural language are scarce. This limitation of current datasets is due to the expensive human manual annotation required and to the highly challenging task of explaining the language formation process from the perspective of the underlying story, as a complex system of interconnected events in space and time. Through a thorough analysis of recently published methods and avai","authors_text":"Marius Leordeanu, Mihai Masala","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T09:33:19Z","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04815","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":"sha256:3fdf4ab4bad0d404f4fd288bc1820cb406d8b1327c43fac9634cad473dd7785f","target":"record","created_at":"2026-07-05T11:32:54Z","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":"9db59cec38fec097d466d933972ae95f0b532f0438b980f564b5fabe1fe9064a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T09:33:19Z","title_canon_sha256":"ce355c484bc03d62e4f7bb41a6b9de294996e32e300c4e73e1b0451cdd284585"},"schema_version":"1.0","source":{"id":"2507.04815","kind":"arxiv","version":1}},"canonical_sha256":"f133a8b14324b0aa750d4d174dbd43c2cd9a14d0578675e032127c9814d8153c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f133a8b14324b0aa750d4d174dbd43c2cd9a14d0578675e032127c9814d8153c","first_computed_at":"2026-07-05T11:32:54.637120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:54.637120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BlTUDoRYMzvm9mYahT8BWUF4SSDOgbySKgfwpNcMpqdEPdb7ss+VAuvkqJt+sZrPHt6bX5U7H6XQ7Wp4cXRYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:54.637638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fdf4ab4bad0d404f4fd288bc1820cb406d8b1327c43fac9634cad473dd7785f","sha256:f80d8d2210afae8bfcbafa59b24aab976ce43285710d78ac07c4d20fadfa4d5e"],"state_sha256":"4610b537647aff92997306c177b8360aa6b532c4e9e377e1ba0e6c0c70a9f850"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fzwyt0zo9m9HCSnvuhltAgM6NsH1qHG5FTWAbSoc2jkaindVv87GzXHZueyAAvnJHwZbD3hIXLdFHVX+Haz3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:48:40.143443Z","bundle_sha256":"80851d4fd6a640711a20c83aabe6c97bb07929b9bf6ff4a7032cd9b33468a80b"}}