{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:G7LIASRI3KQMMX2XIU5EONEMPF","short_pith_number":"pith:G7LIASRI","canonical_record":{"source":{"id":"2405.12710","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"8504acbc924d3bb77baa4497570d52dd40e6a68f7a910e26b423e7d5b4ea9e2e","abstract_canon_sha256":"a745bdf37cbfd270a37edc9124f8ba3f0c8ec16dd0feff5451709a3259ac9dc7"},"schema_version":"1.0"},"canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","source":{"kind":"arxiv","id":"2405.12710","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12710","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12710v3","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12710","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"G7LIASRI3KQM","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"G7LIASRI3KQMMX2X","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"G7LIASRI","created_at":"2026-07-05T08:44:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:G7LIASRI3KQMMX2XIU5EONEMPF","target":"record","payload":{"canonical_record":{"source":{"id":"2405.12710","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"8504acbc924d3bb77baa4497570d52dd40e6a68f7a910e26b423e7d5b4ea9e2e","abstract_canon_sha256":"a745bdf37cbfd270a37edc9124f8ba3f0c8ec16dd0feff5451709a3259ac9dc7"},"schema_version":"1.0"},"canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:14.353340Z","signature_b64":"TEjb0lzjZjip+BwdDJpVdJy5qFUOhugxXQJDOBJJ75o4hGrw4TJR50GRKpJPVuWCunTexSHEoPHJtvYPnRYrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","last_reissued_at":"2026-07-05T08:44:14.352898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:14.352898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.12710","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11+YfujIqL95P9/uS1XcfYjmpnE/cOExHbXfHpAAGbUTmTWJu1Q50TA+8b6fRoBmMptpIffvBFYIahXQjZF4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:02:47.727216Z"},"content_sha256":"a715d304d60af95b629bcceea7181d719d261681dd1b718347b1c69da68c5ed1","schema_version":"1.0","event_id":"sha256:a715d304d60af95b629bcceea7181d719d261681dd1b718347b1c69da68c5ed1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:G7LIASRI3KQMMX2XIU5EONEMPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Zhang, Hengtao Shen, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Xinyu Lyu, Yihang Duan","submitted_at":"2024-05-21T11:59:36Z","abstract_excerpt":"Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12710","kind":"arxiv","version":3},"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/2405.12710/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":"2026-07-05T08:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ua3SPt2JIFIE5gB3nr9BalBYnPmZU+ifeqzFDy3xNGrfqLfVOCwQEtYydPy5SEZVOCLAz/21j9voCGREGlR7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:02:47.727874Z"},"content_sha256":"e02486fa22c38561a25fbfb0cdc82b2d72d3a0f0ddf35c47c57b75b01bbc3aed","schema_version":"1.0","event_id":"sha256:e02486fa22c38561a25fbfb0cdc82b2d72d3a0f0ddf35c47c57b75b01bbc3aed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/bundle.json","state_url":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G7LIASRI3KQMMX2XIU5EONEMPF/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":"2026-07-09T06:02:47Z","links":{"resolver":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF","bundle":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/bundle.json","state":"https://pith.science/pith/G7LIASRI3KQMMX2XIU5EONEMPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G7LIASRI3KQMMX2XIU5EONEMPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G7LIASRI3KQMMX2XIU5EONEMPF","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":"a745bdf37cbfd270a37edc9124f8ba3f0c8ec16dd0feff5451709a3259ac9dc7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:59:36Z","title_canon_sha256":"8504acbc924d3bb77baa4497570d52dd40e6a68f7a910e26b423e7d5b4ea9e2e"},"schema_version":"1.0","source":{"id":"2405.12710","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12710","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12710v3","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12710","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"G7LIASRI3KQM","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"G7LIASRI3KQMMX2X","created_at":"2026-07-05T08:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"G7LIASRI","created_at":"2026-07-05T08:44:14Z"}],"graph_snapshots":[{"event_id":"sha256:e02486fa22c38561a25fbfb0cdc82b2d72d3a0f0ddf35c47c57b75b01bbc3aed","target":"graph","created_at":"2026-07-05T08:44:14Z","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/2405.12710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modal","authors_text":"Haonan Zhang, Hengtao Shen, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Xinyu Lyu, Yihang Duan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:59:36Z","title":"Text-Video Retrieval with Global-Local Semantic Consistent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12710","kind":"arxiv","version":3},"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:a715d304d60af95b629bcceea7181d719d261681dd1b718347b1c69da68c5ed1","target":"record","created_at":"2026-07-05T08:44:14Z","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":"a745bdf37cbfd270a37edc9124f8ba3f0c8ec16dd0feff5451709a3259ac9dc7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T11:59:36Z","title_canon_sha256":"8504acbc924d3bb77baa4497570d52dd40e6a68f7a910e26b423e7d5b4ea9e2e"},"schema_version":"1.0","source":{"id":"2405.12710","kind":"arxiv","version":3}},"canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37d6804a28daa0c65f57453a47348c7956e20c168584995abccda4850bb2af52","first_computed_at":"2026-07-05T08:44:14.352898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:14.352898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TEjb0lzjZjip+BwdDJpVdJy5qFUOhugxXQJDOBJJ75o4hGrw4TJR50GRKpJPVuWCunTexSHEoPHJtvYPnRYrCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:14.353340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12710","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a715d304d60af95b629bcceea7181d719d261681dd1b718347b1c69da68c5ed1","sha256:e02486fa22c38561a25fbfb0cdc82b2d72d3a0f0ddf35c47c57b75b01bbc3aed"],"state_sha256":"20b1c598e2f265f29f9c49640d08736689f285fec1d56a6fc9dec5e2eec72b81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RMBpQ0o1eAKaf3lyqUqjbGICDRbhQkDQHcldchfKl9V2HY4Ecet6vqpUePMMSfLIA+kFTU8otYKbk9/v43y/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:02:47.730944Z","bundle_sha256":"6fd367df992faed8fc32e28c0cad3e61ca81aec36cce4ebdf1d4937a88395826"}}