{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7BDCJKHEVOAOMCRWNSNDOPTKUU","short_pith_number":"pith:7BDCJKHE","canonical_record":{"source":{"id":"2112.01832","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2021-12-03T10:41:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"00f929e2024dcb20d68b478896f0f6de7e86e12971e12f9e60c4bdf85f1e86b8","abstract_canon_sha256":"eb7b4011c67995affb96e594963ed0b0c6e4b21d911c47cb756180c778a5bb44"},"schema_version":"1.0"},"canonical_sha256":"f84624a8e4ab80e60a366c9a373e6aa52692e9b282b8b6cd7182db8019ac7820","source":{"kind":"arxiv","id":"2112.01832","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01832","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01832v3","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01832","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"7BDCJKHEVOAO","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"7BDCJKHEVOAOMCRW","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"7BDCJKHE","created_at":"2026-07-05T04:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7BDCJKHEVOAOMCRWNSNDOPTKUU","target":"record","payload":{"canonical_record":{"source":{"id":"2112.01832","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2021-12-03T10:41:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"00f929e2024dcb20d68b478896f0f6de7e86e12971e12f9e60c4bdf85f1e86b8","abstract_canon_sha256":"eb7b4011c67995affb96e594963ed0b0c6e4b21d911c47cb756180c778a5bb44"},"schema_version":"1.0"},"canonical_sha256":"f84624a8e4ab80e60a366c9a373e6aa52692e9b282b8b6cd7182db8019ac7820","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:58.913057Z","signature_b64":"MTRzOOxwB7XBq+IPgiVFRppjwOcubOQTJ+PSbPnBZnfDwsZMYOlGMsU3SQI0Srey1d+OtM95CwCCPUPOP07GDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f84624a8e4ab80e60a366c9a373e6aa52692e9b282b8b6cd7182db8019ac7820","last_reissued_at":"2026-07-05T04:43:58.912459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:58.912459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.01832","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":"2026-07-05T04:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5I9TWPJdvz3+orsIzMED1WFxyb6XV0CukIptleJfDrVe7UP5z8ADy3/o7shh4xD0slz/8p6OUV+Kw2roXD8nBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:46:17.440656Z"},"content_sha256":"231365b4a6d222e27fb1d3c28af71f8b4876a6bd98ba5008aa20124ee89a0842","schema_version":"1.0","event_id":"sha256:231365b4a6d222e27fb1d3c28af71f8b4876a6bd98ba5008aa20124ee89a0842"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7BDCJKHEVOAOMCRWNSNDOPTKUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Aozhu Chen, Fangming Zhou, Fan Hu, Jianfeng Dong, Xirong Li, Ziyue Wang","submitted_at":"2021-12-03T10:41:12Z","abstract_excerpt":"In this paper we revisit feature fusion, an old-fashioned topic, in the new context of text-to-video retrieval. Different from previous research that considers feature fusion only at one end, let it be video or text, we aim for feature fusion for both ends within a unified framework. We hypothesize that optimizing the convex combination of the features is preferred to modeling their correlations by computationally heavy multi-head self attention. We propose Lightweight Attentional Feature Fusion (LAFF). LAFF performs feature fusion at both early and late stages and at both video and text ends,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01832","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/2112.01832/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":"2026-07-05T04:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UxQTChfr1+4CGPzmjRAVIPCHxjskOZTfBZ0bCme39arvvKOfE3a9XlY4O1Ip67t+bzQpwJP9ObPTevY8JPrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:46:17.441173Z"},"content_sha256":"2ecb4075b4e5ff27d43b85d5c229ba48d68b1239bb165752e385c6bb81767148","schema_version":"1.0","event_id":"sha256:2ecb4075b4e5ff27d43b85d5c229ba48d68b1239bb165752e385c6bb81767148"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU/bundle.json","state_url":"https://pith.science/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU/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":"2026-08-21T21:46:17Z","links":{"resolver":"https://pith.science/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU","bundle":"https://pith.science/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU/bundle.json","state":"https://pith.science/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BDCJKHEVOAOMCRWNSNDOPTKUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7BDCJKHEVOAOMCRWNSNDOPTKUU","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":"eb7b4011c67995affb96e594963ed0b0c6e4b21d911c47cb756180c778a5bb44","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2021-12-03T10:41:12Z","title_canon_sha256":"00f929e2024dcb20d68b478896f0f6de7e86e12971e12f9e60c4bdf85f1e86b8"},"schema_version":"1.0","source":{"id":"2112.01832","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01832","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01832v3","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01832","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"7BDCJKHEVOAO","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"7BDCJKHEVOAOMCRW","created_at":"2026-07-05T04:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"7BDCJKHE","created_at":"2026-07-05T04:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:2ecb4075b4e5ff27d43b85d5c229ba48d68b1239bb165752e385c6bb81767148","target":"graph","created_at":"2026-07-05T04:43:58Z","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/2112.01832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we revisit feature fusion, an old-fashioned topic, in the new context of text-to-video retrieval. Different from previous research that considers feature fusion only at one end, let it be video or text, we aim for feature fusion for both ends within a unified framework. We hypothesize that optimizing the convex combination of the features is preferred to modeling their correlations by computationally heavy multi-head self attention. We propose Lightweight Attentional Feature Fusion (LAFF). LAFF performs feature fusion at both early and late stages and at both video and text ends,","authors_text":"Aozhu Chen, Fangming Zhou, Fan Hu, Jianfeng Dong, Xirong Li, Ziyue Wang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2021-12-03T10:41:12Z","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01832","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":"sha256:231365b4a6d222e27fb1d3c28af71f8b4876a6bd98ba5008aa20124ee89a0842","target":"record","created_at":"2026-07-05T04:43:58Z","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":"eb7b4011c67995affb96e594963ed0b0c6e4b21d911c47cb756180c778a5bb44","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2021-12-03T10:41:12Z","title_canon_sha256":"00f929e2024dcb20d68b478896f0f6de7e86e12971e12f9e60c4bdf85f1e86b8"},"schema_version":"1.0","source":{"id":"2112.01832","kind":"arxiv","version":3}},"canonical_sha256":"f84624a8e4ab80e60a366c9a373e6aa52692e9b282b8b6cd7182db8019ac7820","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f84624a8e4ab80e60a366c9a373e6aa52692e9b282b8b6cd7182db8019ac7820","first_computed_at":"2026-07-05T04:43:58.912459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:58.912459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MTRzOOxwB7XBq+IPgiVFRppjwOcubOQTJ+PSbPnBZnfDwsZMYOlGMsU3SQI0Srey1d+OtM95CwCCPUPOP07GDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:58.913057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01832","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:231365b4a6d222e27fb1d3c28af71f8b4876a6bd98ba5008aa20124ee89a0842","sha256:2ecb4075b4e5ff27d43b85d5c229ba48d68b1239bb165752e385c6bb81767148"],"state_sha256":"32fbb1ec43387e1d9fae1ed50492512bbd20c420b5787ddda4783c2475dffbbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3gNDMjsP9qq2arg18ebNCKBR/ms7dnuwgHqrKEBRbL6Ux3w2LjeWlmdpNeDJ7PGqmcKoxCVEcHtC5Wr11g8MCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:46:17.446733Z","bundle_sha256":"c360ce9a8943d324700f59d5ca01b3b7fc9640185aec6c35887af7915831ac37"}}