{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UJYODH7GO2MNBLRWJXGO7TPEVI","short_pith_number":"pith:UJYODH7G","canonical_record":{"source":{"id":"2109.14910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T08:12:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a01f8d0a15c873310e19dcfcf0dfed477df399eca4b2e9c8266d5cccfb695cb1","abstract_canon_sha256":"f430f7f792156ce2c4f0c3dbef35525ca4b3c8f1257fd9026cdce62f8ebfa623"},"schema_version":"1.0"},"canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","source":{"kind":"arxiv","id":"2109.14910","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.14910","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2109.14910v1","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14910","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"UJYODH7GO2MN","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"UJYODH7GO2MNBLRW","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"UJYODH7G","created_at":"2026-07-05T03:18:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UJYODH7GO2MNBLRWJXGO7TPEVI","target":"record","payload":{"canonical_record":{"source":{"id":"2109.14910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T08:12:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a01f8d0a15c873310e19dcfcf0dfed477df399eca4b2e9c8266d5cccfb695cb1","abstract_canon_sha256":"f430f7f792156ce2c4f0c3dbef35525ca4b3c8f1257fd9026cdce62f8ebfa623"},"schema_version":"1.0"},"canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:45.558288Z","signature_b64":"qDIkcRc9UNY0/myVyvSMNYGi2QdAFGMGigal6Kwa5d7UEDU9lUPrl/mvcSscJhdiJ6NsZ0Z7DAehABpQgYNBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","last_reissued_at":"2026-07-05T03:18:45.557952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:45.557952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.14910","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":"2026-07-05T03:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9F486vsMZYZTc37fA1GdqI+korSR1Y0mhQu3mp/yuJ5IccAWsq6L5/mvTqOOwDu3OarXUUYGgpzc2pzP93N2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:29:52.461600Z"},"content_sha256":"bce0dfa4fe7413bc446419b109bb8fc82cc99279eee994f1a2f2f091cf81f103","schema_version":"1.0","event_id":"sha256:bce0dfa4fe7413bc446419b109bb8fc82cc99279eee994f1a2f2f091cf81f103"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UJYODH7GO2MNBLRWJXGO7TPEVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Mohammadreza Zolfaghari, Peter Gehler, Thomas Brox, Yi Zhu","submitted_at":"2021-09-30T08:12:21Z","abstract_excerpt":"Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14910","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/2109.14910/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":"2026-07-05T03:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtHuBffHHpv6NZ6mq3Ix3prU2qncQ1SgQUnJYpkAtgsh67HKYKNklkmM9unpZyzPP3VoXDEqH/r/9jlAGIpUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:29:52.462732Z"},"content_sha256":"b1938b2444978e321dbf235d3a0b2658e80cf1c3589526de12a8d8e64a0cfef3","schema_version":"1.0","event_id":"sha256:b1938b2444978e321dbf235d3a0b2658e80cf1c3589526de12a8d8e64a0cfef3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/bundle.json","state_url":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/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":"2026-08-14T02:29:52Z","links":{"resolver":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI","bundle":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/bundle.json","state":"https://pith.science/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJYODH7GO2MNBLRWJXGO7TPEVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UJYODH7GO2MNBLRWJXGO7TPEVI","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":"f430f7f792156ce2c4f0c3dbef35525ca4b3c8f1257fd9026cdce62f8ebfa623","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T08:12:21Z","title_canon_sha256":"a01f8d0a15c873310e19dcfcf0dfed477df399eca4b2e9c8266d5cccfb695cb1"},"schema_version":"1.0","source":{"id":"2109.14910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.14910","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2109.14910v1","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14910","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"UJYODH7GO2MN","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"UJYODH7GO2MNBLRW","created_at":"2026-07-05T03:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"UJYODH7G","created_at":"2026-07-05T03:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:b1938b2444978e321dbf235d3a0b2658e80cf1c3589526de12a8d8e64a0cfef3","target":"graph","created_at":"2026-07-05T03:18:45Z","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/2109.14910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of the","authors_text":"Mohammadreza Zolfaghari, Peter Gehler, Thomas Brox, Yi Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T08:12:21Z","title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14910","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:bce0dfa4fe7413bc446419b109bb8fc82cc99279eee994f1a2f2f091cf81f103","target":"record","created_at":"2026-07-05T03:18:45Z","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":"f430f7f792156ce2c4f0c3dbef35525ca4b3c8f1257fd9026cdce62f8ebfa623","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T08:12:21Z","title_canon_sha256":"a01f8d0a15c873310e19dcfcf0dfed477df399eca4b2e9c8266d5cccfb695cb1"},"schema_version":"1.0","source":{"id":"2109.14910","kind":"arxiv","version":1}},"canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a270e19fe67698d0ae364dccefcde4aa0ef3d39d59553579c4c4a6927f06fc74","first_computed_at":"2026-07-05T03:18:45.557952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:18:45.557952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qDIkcRc9UNY0/myVyvSMNYGi2QdAFGMGigal6Kwa5d7UEDU9lUPrl/mvcSscJhdiJ6NsZ0Z7DAehABpQgYNBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:18:45.558288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.14910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bce0dfa4fe7413bc446419b109bb8fc82cc99279eee994f1a2f2f091cf81f103","sha256:b1938b2444978e321dbf235d3a0b2658e80cf1c3589526de12a8d8e64a0cfef3"],"state_sha256":"bbcac22ec6afdc3b22aba1cdf1fcaf704ca6541d9fa0ed60c6606508a6aa4832"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2odUgS5UOE4JF9ejPrWuYvFcSd0vJJOVNvhstKUYgY/V3nVYa4FoTlniCgIz6JTBEISlQQLdyTs/lECDFZw1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T02:29:52.471127Z","bundle_sha256":"5fd6d84427833e5eef8c8f79927f37c46cb92928521dbfff3c18f6b7d8a7f956"}}