{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BPW64G4DWHGQIFEUBTG3D2TAII","short_pith_number":"pith:BPW64G4D","canonical_record":{"source":{"id":"2305.07910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-13T12:31:37Z","cross_cats_sorted":[],"title_canon_sha256":"90ed920361dfb2435d5d6eb88073365d09d7d4391afc177a8cfd80fc92458967","abstract_canon_sha256":"d282ce74424ac18ff78fd3165d2f1e4d1eba7dd21562d5903198a213c456bed5"},"schema_version":"1.0"},"canonical_sha256":"0bedee1b83b1cd0414940ccdb1ea604215d077073e8f29ac213747778029bbe8","source":{"kind":"arxiv","id":"2305.07910","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07910","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07910v1","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07910","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"BPW64G4DWHGQ","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"BPW64G4DWHGQIFEU","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"BPW64G4D","created_at":"2026-07-05T06:09:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BPW64G4DWHGQIFEUBTG3D2TAII","target":"record","payload":{"canonical_record":{"source":{"id":"2305.07910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-13T12:31:37Z","cross_cats_sorted":[],"title_canon_sha256":"90ed920361dfb2435d5d6eb88073365d09d7d4391afc177a8cfd80fc92458967","abstract_canon_sha256":"d282ce74424ac18ff78fd3165d2f1e4d1eba7dd21562d5903198a213c456bed5"},"schema_version":"1.0"},"canonical_sha256":"0bedee1b83b1cd0414940ccdb1ea604215d077073e8f29ac213747778029bbe8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:55.637959Z","signature_b64":"KRH/xSwPsf42eAyQ9CYOWReO8A3+QVvuarOFckYQS314xJOfObfN+8F6anrI/kRivZlZG1ylRVEVlXln4MVWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bedee1b83b1cd0414940ccdb1ea604215d077073e8f29ac213747778029bbe8","last_reissued_at":"2026-07-05T06:09:55.637578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:55.637578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.07910","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":"2026-07-05T06:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFb+m1+FTHz1ac/d4nB98s3ntD+aYE1i45X13f6H/q4mesT7ZCql0myXdOHqAb9Hs7AErefHWlWVuxbsLY02Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:14:34.962765Z"},"content_sha256":"9449fce9423f8658572b081b6f91ea170e8b26f6ae4cd9833b7b4e386abe3699","schema_version":"1.0","event_id":"sha256:9449fce9423f8658572b081b6f91ea170e8b26f6ae4cd9833b7b4e386abe3699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BPW64G4DWHGQIFEUBTG3D2TAII","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ban, Han Fang, Hao Sun, Xianghao Zang, Zhifei Yang","submitted_at":"2023-05-13T12:31:37Z","abstract_excerpt":"Recently, masked video modeling has been widely explored and significantly improved the model's understanding ability of visual regions at a local level. However, existing methods usually adopt random masking and follow the same reconstruction paradigm to complete the masked regions, which do not leverage the correlations between cross-modal content. In this paper, we present Mask for Semantics Completion (MASCOT) based on semantic-based masked modeling. Specifically, after applying attention-based video masking to generate high-informed and low-informed masks, we propose Informed Semantics Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07910","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/2305.07910/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":"2026-07-05T06:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3YvBM+Wgd3/P+nuGIrMIFj76GRrBUoNEWtE9x62OxJYi8iIyFLpOjGk/1BWMDZXteeLyUt7gwmkSXqApc9l7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:14:34.964378Z"},"content_sha256":"cb2f2a9a20175a58df9c8d570437f85993e16b2ad2d4d5f9b74608bcbfa73dbf","schema_version":"1.0","event_id":"sha256:cb2f2a9a20175a58df9c8d570437f85993e16b2ad2d4d5f9b74608bcbfa73dbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPW64G4DWHGQIFEUBTG3D2TAII/bundle.json","state_url":"https://pith.science/pith/BPW64G4DWHGQIFEUBTG3D2TAII/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPW64G4DWHGQIFEUBTG3D2TAII/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":"2026-08-07T19:14:34Z","links":{"resolver":"https://pith.science/pith/BPW64G4DWHGQIFEUBTG3D2TAII","bundle":"https://pith.science/pith/BPW64G4DWHGQIFEUBTG3D2TAII/bundle.json","state":"https://pith.science/pith/BPW64G4DWHGQIFEUBTG3D2TAII/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPW64G4DWHGQIFEUBTG3D2TAII/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BPW64G4DWHGQIFEUBTG3D2TAII","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":"d282ce74424ac18ff78fd3165d2f1e4d1eba7dd21562d5903198a213c456bed5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-13T12:31:37Z","title_canon_sha256":"90ed920361dfb2435d5d6eb88073365d09d7d4391afc177a8cfd80fc92458967"},"schema_version":"1.0","source":{"id":"2305.07910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07910","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07910v1","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07910","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"BPW64G4DWHGQ","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"BPW64G4DWHGQIFEU","created_at":"2026-07-05T06:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"BPW64G4D","created_at":"2026-07-05T06:09:55Z"}],"graph_snapshots":[{"event_id":"sha256:cb2f2a9a20175a58df9c8d570437f85993e16b2ad2d4d5f9b74608bcbfa73dbf","target":"graph","created_at":"2026-07-05T06:09:55Z","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/2305.07910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, masked video modeling has been widely explored and significantly improved the model's understanding ability of visual regions at a local level. However, existing methods usually adopt random masking and follow the same reconstruction paradigm to complete the masked regions, which do not leverage the correlations between cross-modal content. In this paper, we present Mask for Semantics Completion (MASCOT) based on semantic-based masked modeling. Specifically, after applying attention-based video masking to generate high-informed and low-informed masks, we propose Informed Semantics Co","authors_text":"Chao Ban, Han Fang, Hao Sun, Xianghao Zang, Zhifei Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-13T12:31:37Z","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07910","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":"sha256:9449fce9423f8658572b081b6f91ea170e8b26f6ae4cd9833b7b4e386abe3699","target":"record","created_at":"2026-07-05T06:09:55Z","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":"d282ce74424ac18ff78fd3165d2f1e4d1eba7dd21562d5903198a213c456bed5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-13T12:31:37Z","title_canon_sha256":"90ed920361dfb2435d5d6eb88073365d09d7d4391afc177a8cfd80fc92458967"},"schema_version":"1.0","source":{"id":"2305.07910","kind":"arxiv","version":1}},"canonical_sha256":"0bedee1b83b1cd0414940ccdb1ea604215d077073e8f29ac213747778029bbe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bedee1b83b1cd0414940ccdb1ea604215d077073e8f29ac213747778029bbe8","first_computed_at":"2026-07-05T06:09:55.637578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:55.637578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KRH/xSwPsf42eAyQ9CYOWReO8A3+QVvuarOFckYQS314xJOfObfN+8F6anrI/kRivZlZG1ylRVEVlXln4MVWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:55.637959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9449fce9423f8658572b081b6f91ea170e8b26f6ae4cd9833b7b4e386abe3699","sha256:cb2f2a9a20175a58df9c8d570437f85993e16b2ad2d4d5f9b74608bcbfa73dbf"],"state_sha256":"cc7279553f7c4f07095a6666c4a9369cd12fe8981631820054034f2eb4f34374"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AqdxXZOn+dOOZKaYQHz4W1dAXysHobHEGhHX+vfeWDFGr+BLBOr8Oaykl0F3xi2l03vOGmPZDWQG374xCJA+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:14:34.970838Z","bundle_sha256":"85e07bfd1b65741301e8fe1f9f9ccd1f937c8a3c3e949263e9e11248b54bfc1a"}}