{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GF7G3333LDMMVXIBRCYNWRJL4V","short_pith_number":"pith:GF7G3333","canonical_record":{"source":{"id":"2304.02080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T19:11:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d8df82e8002917b82e1c8951ade970374cfa0aaf3914bad56da6573e1876fe99","abstract_canon_sha256":"70490c108312bee28e772a9bc0b7348a2930a781546416c9ff1d943a912e22ba"},"schema_version":"1.0"},"canonical_sha256":"317e6def7b58d8cadd0188b0db452be577cb803254f8c4f1d11bf86365896cd2","source":{"kind":"arxiv","id":"2304.02080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02080","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02080v1","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02080","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"GF7G3333LDMM","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"GF7G3333LDMMVXIB","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"GF7G3333","created_at":"2026-07-05T05:58:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GF7G3333LDMMVXIBRCYNWRJL4V","target":"record","payload":{"canonical_record":{"source":{"id":"2304.02080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T19:11:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d8df82e8002917b82e1c8951ade970374cfa0aaf3914bad56da6573e1876fe99","abstract_canon_sha256":"70490c108312bee28e772a9bc0b7348a2930a781546416c9ff1d943a912e22ba"},"schema_version":"1.0"},"canonical_sha256":"317e6def7b58d8cadd0188b0db452be577cb803254f8c4f1d11bf86365896cd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:21.701482Z","signature_b64":"+lP8Kb6XWQkGfn3ea7/tWrX5HEjTAkcWX/4qxQQDypeXiWu6chJT7xwpseup0o4iQL9MCn3MmLlG+0WLyYA5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"317e6def7b58d8cadd0188b0db452be577cb803254f8c4f1d11bf86365896cd2","last_reissued_at":"2026-07-05T05:58:21.700985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:21.700985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.02080","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":"2026-07-05T05:58:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFwAHkLiMU4332BsLQ9ESh/sn6cFYw6bNHOaVYwqv50/QCDzzWMqSfqif+zi3bBMiiPfxYPPLLXzU6ESbYu5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:41:56.955304Z"},"content_sha256":"5405a95abca3f9d3c6197ada53d42ca61ab7bfeb5708bf49e8d61c55c0f7c3f2","schema_version":"1.0","event_id":"sha256:5405a95abca3f9d3c6197ada53d42ca61ab7bfeb5708bf49e8d61c55c0f7c3f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GF7G3333LDMMVXIBRCYNWRJL4V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rumshisky, David Chan, Shalini Ghosh, Stephen Rawls, Vladislav Lialin, Wael Hamza","submitted_at":"2023-04-04T19:11:05Z","abstract_excerpt":"Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale video-text datasets and mining techniques suffer from several limitations, such as the scarcity of aligned data, the lack of diversity in the data, and the difficulty of collecting aligned data. Currently popular video-text data mining approach via automatic speech recognition (ASR) used in HowTo100M provides low-quality captions that often do not refer to the vide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02080","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/2304.02080/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":"2026-07-05T05:58:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIHgHpKJWrM9Bqy1Zp7pbzeHB0DzzqpXC74Q5rIiqA98Ngu0elLdbfek3uDjLzo2t16li3PhzyX0GT0w3Y40DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:41:56.955714Z"},"content_sha256":"4a84a8e89d957be06ff195accaf262b443fe7367588765878df3b18611f38c64","schema_version":"1.0","event_id":"sha256:4a84a8e89d957be06ff195accaf262b443fe7367588765878df3b18611f38c64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GF7G3333LDMMVXIBRCYNWRJL4V/bundle.json","state_url":"https://pith.science/pith/GF7G3333LDMMVXIBRCYNWRJL4V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GF7G3333LDMMVXIBRCYNWRJL4V/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":"2026-07-09T02:41:56Z","links":{"resolver":"https://pith.science/pith/GF7G3333LDMMVXIBRCYNWRJL4V","bundle":"https://pith.science/pith/GF7G3333LDMMVXIBRCYNWRJL4V/bundle.json","state":"https://pith.science/pith/GF7G3333LDMMVXIBRCYNWRJL4V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GF7G3333LDMMVXIBRCYNWRJL4V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GF7G3333LDMMVXIBRCYNWRJL4V","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":"70490c108312bee28e772a9bc0b7348a2930a781546416c9ff1d943a912e22ba","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T19:11:05Z","title_canon_sha256":"d8df82e8002917b82e1c8951ade970374cfa0aaf3914bad56da6573e1876fe99"},"schema_version":"1.0","source":{"id":"2304.02080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02080","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02080v1","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02080","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"GF7G3333LDMM","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"GF7G3333LDMMVXIB","created_at":"2026-07-05T05:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"GF7G3333","created_at":"2026-07-05T05:58:21Z"}],"graph_snapshots":[{"event_id":"sha256:4a84a8e89d957be06ff195accaf262b443fe7367588765878df3b18611f38c64","target":"graph","created_at":"2026-07-05T05:58:21Z","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/2304.02080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale video-text datasets and mining techniques suffer from several limitations, such as the scarcity of aligned data, the lack of diversity in the data, and the difficulty of collecting aligned data. Currently popular video-text data mining approach via automatic speech recognition (ASR) used in HowTo100M provides low-quality captions that often do not refer to the vide","authors_text":"Anna Rumshisky, David Chan, Shalini Ghosh, Stephen Rawls, Vladislav Lialin, Wael Hamza","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T19:11:05Z","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02080","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":"sha256:5405a95abca3f9d3c6197ada53d42ca61ab7bfeb5708bf49e8d61c55c0f7c3f2","target":"record","created_at":"2026-07-05T05:58:21Z","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":"70490c108312bee28e772a9bc0b7348a2930a781546416c9ff1d943a912e22ba","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-04T19:11:05Z","title_canon_sha256":"d8df82e8002917b82e1c8951ade970374cfa0aaf3914bad56da6573e1876fe99"},"schema_version":"1.0","source":{"id":"2304.02080","kind":"arxiv","version":1}},"canonical_sha256":"317e6def7b58d8cadd0188b0db452be577cb803254f8c4f1d11bf86365896cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"317e6def7b58d8cadd0188b0db452be577cb803254f8c4f1d11bf86365896cd2","first_computed_at":"2026-07-05T05:58:21.700985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:21.700985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+lP8Kb6XWQkGfn3ea7/tWrX5HEjTAkcWX/4qxQQDypeXiWu6chJT7xwpseup0o4iQL9MCn3MmLlG+0WLyYA5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:21.701482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5405a95abca3f9d3c6197ada53d42ca61ab7bfeb5708bf49e8d61c55c0f7c3f2","sha256:4a84a8e89d957be06ff195accaf262b443fe7367588765878df3b18611f38c64"],"state_sha256":"6e306443d1c70fc71b3d41573dcb9bf95ba752a4cb8347b662232f22d1dcd73e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Va/bbyVCAME91siWTKPVmgpxnGZD50XXTlwZqZzmohnQKRqSQqPBDm1+Z1cS+g7IS6nGuBbXn8zOk2XzTAICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:41:56.957790Z","bundle_sha256":"537bca87fe0a3e7e899ffe16f77df65d813328a51b6b6f4d2b1f9f3186e12ea3"}}