{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TXXCOXSASZBQWFJV5Z3LMQMXIF","short_pith_number":"pith:TXXCOXSA","canonical_record":{"source":{"id":"2301.07463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:15:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cec2bf917fdcd289edab6e5efc59cbd745ad90e2ec3677d2fb5eac365c1f773","abstract_canon_sha256":"a19eacb69a25d0a1fce7a6aeeda64e76687d1dd5a7a4078791381d3062bd4351"},"schema_version":"1.0"},"canonical_sha256":"9dee275e4096430b1535ee76b6419741592c7a5bc0c11388aca2c75527c4eafc","source":{"kind":"arxiv","id":"2301.07463","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07463","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07463v1","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07463","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"TXXCOXSASZBQ","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"TXXCOXSASZBQWFJV","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"TXXCOXSA","created_at":"2026-07-05T05:34:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TXXCOXSASZBQWFJV5Z3LMQMXIF","target":"record","payload":{"canonical_record":{"source":{"id":"2301.07463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:15:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cec2bf917fdcd289edab6e5efc59cbd745ad90e2ec3677d2fb5eac365c1f773","abstract_canon_sha256":"a19eacb69a25d0a1fce7a6aeeda64e76687d1dd5a7a4078791381d3062bd4351"},"schema_version":"1.0"},"canonical_sha256":"9dee275e4096430b1535ee76b6419741592c7a5bc0c11388aca2c75527c4eafc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:09.459723Z","signature_b64":"L+a3QtjiTHJ3FLUIVP9ZiERlQl79bEzKG8HOKWY3CCiIUIWjSzhqTWPGFCo+Cwh/wyboQ+huvZiEC1iYifnqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dee275e4096430b1535ee76b6419741592c7a5bc0c11388aca2c75527c4eafc","last_reissued_at":"2026-07-05T05:34:09.459298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:09.459298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.07463","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":"2026-07-05T05:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1p+viivQaeR8gIUcwxw8NEN2JDYbvVquJOc46/f+h6kziucYZ52vfNU75tGt5ojXHIrcxqqaOx+RkHZIxsMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:21:21.931065Z"},"content_sha256":"1335149bdab101e7fa2839f7e0635edc0b9bb8a4fef870ef61ea7692816449c8","schema_version":"1.0","event_id":"sha256:1335149bdab101e7fa2839f7e0635edc0b9bb8a4fef870ef61ea7692816449c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TXXCOXSASZBQWFJV5Z3LMQMXIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal Perceiving Video-Language Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fan Ma, Heng Wang, Jiashi Feng, Jingjia Huang, Linchao Zhu, Xiaojie Jin, Yi Yang","submitted_at":"2023-01-18T12:15:47Z","abstract_excerpt":"Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the local associations between videos and texts are not modeled, restricting the pre-training models' generality, especially for tasks requiring the temporal video boundary for certain query texts. This work introduces a novel text-video localization pre-text task to enable fine-grained temporal and semantic alignment such that the trained model can accurately perce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07463","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/2301.07463/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":"2026-07-05T05:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EPkailkT07Ysu4xy29p7fgBh/W6OtPlcweQndX1VY8xM/B+26V/JU3l9t94Wmf7HVULUvbxngmRP6Yzfqa6iCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:21:21.931659Z"},"content_sha256":"dbe6142818c139a411433a88633b8236699d94321d349220c3e716dd0141c084","schema_version":"1.0","event_id":"sha256:dbe6142818c139a411433a88633b8236699d94321d349220c3e716dd0141c084"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF/bundle.json","state_url":"https://pith.science/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF/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":"2026-08-06T00:21:21Z","links":{"resolver":"https://pith.science/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF","bundle":"https://pith.science/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF/bundle.json","state":"https://pith.science/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXXCOXSASZBQWFJV5Z3LMQMXIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TXXCOXSASZBQWFJV5Z3LMQMXIF","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":"a19eacb69a25d0a1fce7a6aeeda64e76687d1dd5a7a4078791381d3062bd4351","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:15:47Z","title_canon_sha256":"1cec2bf917fdcd289edab6e5efc59cbd745ad90e2ec3677d2fb5eac365c1f773"},"schema_version":"1.0","source":{"id":"2301.07463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07463","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07463v1","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07463","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"TXXCOXSASZBQ","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"TXXCOXSASZBQWFJV","created_at":"2026-07-05T05:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"TXXCOXSA","created_at":"2026-07-05T05:34:09Z"}],"graph_snapshots":[{"event_id":"sha256:dbe6142818c139a411433a88633b8236699d94321d349220c3e716dd0141c084","target":"graph","created_at":"2026-07-05T05:34:09Z","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/2301.07463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the local associations between videos and texts are not modeled, restricting the pre-training models' generality, especially for tasks requiring the temporal video boundary for certain query texts. This work introduces a novel text-video localization pre-text task to enable fine-grained temporal and semantic alignment such that the trained model can accurately perce","authors_text":"Fan Ma, Heng Wang, Jiashi Feng, Jingjia Huang, Linchao Zhu, Xiaojie Jin, Yi Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:15:47Z","title":"Temporal Perceiving Video-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07463","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":"sha256:1335149bdab101e7fa2839f7e0635edc0b9bb8a4fef870ef61ea7692816449c8","target":"record","created_at":"2026-07-05T05:34:09Z","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":"a19eacb69a25d0a1fce7a6aeeda64e76687d1dd5a7a4078791381d3062bd4351","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-18T12:15:47Z","title_canon_sha256":"1cec2bf917fdcd289edab6e5efc59cbd745ad90e2ec3677d2fb5eac365c1f773"},"schema_version":"1.0","source":{"id":"2301.07463","kind":"arxiv","version":1}},"canonical_sha256":"9dee275e4096430b1535ee76b6419741592c7a5bc0c11388aca2c75527c4eafc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dee275e4096430b1535ee76b6419741592c7a5bc0c11388aca2c75527c4eafc","first_computed_at":"2026-07-05T05:34:09.459298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:09.459298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+a3QtjiTHJ3FLUIVP9ZiERlQl79bEzKG8HOKWY3CCiIUIWjSzhqTWPGFCo+Cwh/wyboQ+huvZiEC1iYifnqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:09.459723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.07463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1335149bdab101e7fa2839f7e0635edc0b9bb8a4fef870ef61ea7692816449c8","sha256:dbe6142818c139a411433a88633b8236699d94321d349220c3e716dd0141c084"],"state_sha256":"c0633c995236b81855d9f65d695fefbac61ff2f49ea3ce273a74b29bd44485f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"04is13pIqYzCFjg+oLL0xMgn4UvnITXy0M9o/eeS8Yf1vkSamtKFxxXqUR0TOQ6xy1xoc/RH/aiEw/SBopXrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:21:21.937571Z","bundle_sha256":"f3e85951c3854e83fabcea36f92627a30b037db648dc531b390522525ddece9c"}}