{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3N4VGZFVEYY3JBPHXCK26DKEFT","short_pith_number":"pith:3N4VGZFV","canonical_record":{"source":{"id":"2112.00656","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T17:06:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aa9bc0448eda2d116463f4910ce7993a95644df78c1f8792aeaf3e5c6cea0ba4","abstract_canon_sha256":"3b7c9b7d5402a241b2ea44b1e3904aa3b47c275e86c6bdf57b862b9bf50986a3"},"schema_version":"1.0"},"canonical_sha256":"db795364b52631b485e7b895af0d442ce8288fa7d8f7a7ca76f5335e047e9f83","source":{"kind":"arxiv","id":"2112.00656","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00656","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00656v6","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00656","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"3N4VGZFVEYY3","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_16","alias_value":"3N4VGZFVEYY3JBPH","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_8","alias_value":"3N4VGZFV","created_at":"2026-07-05T04:24:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3N4VGZFVEYY3JBPHXCK26DKEFT","target":"record","payload":{"canonical_record":{"source":{"id":"2112.00656","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T17:06:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aa9bc0448eda2d116463f4910ce7993a95644df78c1f8792aeaf3e5c6cea0ba4","abstract_canon_sha256":"3b7c9b7d5402a241b2ea44b1e3904aa3b47c275e86c6bdf57b862b9bf50986a3"},"schema_version":"1.0"},"canonical_sha256":"db795364b52631b485e7b895af0d442ce8288fa7d8f7a7ca76f5335e047e9f83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:23.997694Z","signature_b64":"RYmfiVrRRhxEcbcv2+HmXC24b2uHWRjOBItUZ2+ik9oPhUsmUlHazpyrnLXKsG+UQRJzMAhlxCd1x9f64md9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db795364b52631b485e7b895af0d442ce8288fa7d8f7a7ca76f5335e047e9f83","last_reissued_at":"2026-07-05T04:24:23.997251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:23.997251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.00656","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1J+HTN+GwHEqXaiqVMV4Q67GwPyo7UXTEejQ8X8XC1xVZs6sQ2Gf+1sQWpl2LLPszn6tr7b1iCXN1aWcewhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T08:54:54.048064Z"},"content_sha256":"5ff7cdf8f22f18a46d2370d44ce08c5e89e20e17be1c1a738dafd9e2ef53346f","schema_version":"1.0","event_id":"sha256:5ff7cdf8f22f18a46d2370d44ce08c5e89e20e17be1c1a738dafd9e2ef53346f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3N4VGZFVEYY3JBPHXCK26DKEFT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object-aware Video-language Pre-training for Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Guanyu Cai, Mike Zheng Shou, Rui Yan, Xiaohu Qie, Xudong Lin, Ying Shan, Yixiao Ge","submitted_at":"2021-12-01T17:06:39Z","abstract_excerpt":"Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained semantic align. In this work, we present Object-aware Transformers, an object-centric approach that extends video-language transformer to incorporate object representations. The key idea is to leverage the bounding boxes and object tags to guide the training process. We evaluate our model on three standard sub-tasks of video-text matching on four widely used bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00656","kind":"arxiv","version":6},"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/2112.00656/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":"2026-07-05T04:24:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kfTnBeKoP0BgcvQBJ34RD7RcM1vMiTqB3ez/VbxK9W6E0qSWqpfdriBRhPT+8tVyM/yKqdC2S2igcnU2xvACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T08:54:54.048451Z"},"content_sha256":"12e67873596e41793a12292a6d6f99461aa4158e5fc85ffd3c5e802cdfdfaf2d","schema_version":"1.0","event_id":"sha256:12e67873596e41793a12292a6d6f99461aa4158e5fc85ffd3c5e802cdfdfaf2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3N4VGZFVEYY3JBPHXCK26DKEFT/bundle.json","state_url":"https://pith.science/pith/3N4VGZFVEYY3JBPHXCK26DKEFT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3N4VGZFVEYY3JBPHXCK26DKEFT/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":"2026-07-17T08:54:54Z","links":{"resolver":"https://pith.science/pith/3N4VGZFVEYY3JBPHXCK26DKEFT","bundle":"https://pith.science/pith/3N4VGZFVEYY3JBPHXCK26DKEFT/bundle.json","state":"https://pith.science/pith/3N4VGZFVEYY3JBPHXCK26DKEFT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3N4VGZFVEYY3JBPHXCK26DKEFT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3N4VGZFVEYY3JBPHXCK26DKEFT","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":"3b7c9b7d5402a241b2ea44b1e3904aa3b47c275e86c6bdf57b862b9bf50986a3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T17:06:39Z","title_canon_sha256":"aa9bc0448eda2d116463f4910ce7993a95644df78c1f8792aeaf3e5c6cea0ba4"},"schema_version":"1.0","source":{"id":"2112.00656","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00656","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00656v6","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00656","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_12","alias_value":"3N4VGZFVEYY3","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_16","alias_value":"3N4VGZFVEYY3JBPH","created_at":"2026-07-05T04:24:23Z"},{"alias_kind":"pith_short_8","alias_value":"3N4VGZFV","created_at":"2026-07-05T04:24:23Z"}],"graph_snapshots":[{"event_id":"sha256:12e67873596e41793a12292a6d6f99461aa4158e5fc85ffd3c5e802cdfdfaf2d","target":"graph","created_at":"2026-07-05T04:24:23Z","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/2112.00656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained semantic align. In this work, we present Object-aware Transformers, an object-centric approach that extends video-language transformer to incorporate object representations. The key idea is to leverage the bounding boxes and object tags to guide the training process. We evaluate our model on three standard sub-tasks of video-text matching on four widely used bench","authors_text":"Alex Jinpeng Wang, Guanyu Cai, Mike Zheng Shou, Rui Yan, Xiaohu Qie, Xudong Lin, Ying Shan, Yixiao Ge","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T17:06:39Z","title":"Object-aware Video-language Pre-training for Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00656","kind":"arxiv","version":6},"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":"sha256:5ff7cdf8f22f18a46d2370d44ce08c5e89e20e17be1c1a738dafd9e2ef53346f","target":"record","created_at":"2026-07-05T04:24:23Z","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":"3b7c9b7d5402a241b2ea44b1e3904aa3b47c275e86c6bdf57b862b9bf50986a3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-01T17:06:39Z","title_canon_sha256":"aa9bc0448eda2d116463f4910ce7993a95644df78c1f8792aeaf3e5c6cea0ba4"},"schema_version":"1.0","source":{"id":"2112.00656","kind":"arxiv","version":6}},"canonical_sha256":"db795364b52631b485e7b895af0d442ce8288fa7d8f7a7ca76f5335e047e9f83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db795364b52631b485e7b895af0d442ce8288fa7d8f7a7ca76f5335e047e9f83","first_computed_at":"2026-07-05T04:24:23.997251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:23.997251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RYmfiVrRRhxEcbcv2+HmXC24b2uHWRjOBItUZ2+ik9oPhUsmUlHazpyrnLXKsG+UQRJzMAhlxCd1x9f64md9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:23.997694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00656","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ff7cdf8f22f18a46d2370d44ce08c5e89e20e17be1c1a738dafd9e2ef53346f","sha256:12e67873596e41793a12292a6d6f99461aa4158e5fc85ffd3c5e802cdfdfaf2d"],"state_sha256":"623ef0250aa333966a19ac4e04498601a81f844f3bfa72464531e60c061977ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnJjNmQzXCdP5KnujSOqqND0M1WLYkZY8Q2I3dZM0bkb83W/Y6OaA2/Qnd7QGPVDGDIMHM6/l9jat/J0snikCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T08:54:54.050517Z","bundle_sha256":"20eef7798188c476493ef72247f64cc25288480be1b6025725b93bc0eae47bd5"}}