{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MNCPGMNSYRAK6FE5OX2MVWAWEZ","short_pith_number":"pith:MNCPGMNS","canonical_record":{"source":{"id":"2305.08675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:31:49Z","cross_cats_sorted":[],"title_canon_sha256":"5b422b6813dbaae30fdaa69a5fa2a01434e5ae232538957c49b642452ceff9eb","abstract_canon_sha256":"5ddb0b6ca17660fcc9861e7a22f01d06cd6a4b4ddfa2b9b5e79fb49009082319"},"schema_version":"1.0"},"canonical_sha256":"6344f331b2c440af149d75f4cad8162641c9041520285e173dabe1c68ead9f7f","source":{"kind":"arxiv","id":"2305.08675","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08675","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08675v2","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08675","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"MNCPGMNSYRAK","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"pith_short_16","alias_value":"MNCPGMNSYRAK6FE5","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"pith_short_8","alias_value":"MNCPGMNS","created_at":"2026-07-05T07:08:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MNCPGMNSYRAK6FE5OX2MVWAWEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:31:49Z","cross_cats_sorted":[],"title_canon_sha256":"5b422b6813dbaae30fdaa69a5fa2a01434e5ae232538957c49b642452ceff9eb","abstract_canon_sha256":"5ddb0b6ca17660fcc9861e7a22f01d06cd6a4b4ddfa2b9b5e79fb49009082319"},"schema_version":"1.0"},"canonical_sha256":"6344f331b2c440af149d75f4cad8162641c9041520285e173dabe1c68ead9f7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:57.395837Z","signature_b64":"d63OG3hsN0eFnr1yw0DTgpBq35vn/PIB/UEb3ZOWexHtHROMa5MWFzSqbAnFFKyJEqMB4eYK7pwsHxD4t4mSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6344f331b2c440af149d75f4cad8162641c9041520285e173dabe1c68ead9f7f","last_reissued_at":"2026-07-05T07:08:57.395289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:57.395289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08675","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGdNnGvxcjAm24hRvcBHDi+9FNHKWrCbcXDBeYauNFWcPgfJq3rrrc7tahb+drBsm7If86Fg9ID7qiAVOwiFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:37:36.684862Z"},"content_sha256":"1f575be9ee8232158ef09f07d8ca7635b3b34bc4079d14f8f7d98b082dbc0f08","schema_version":"1.0","event_id":"sha256:1f575be9ee8232158ef09f07d8ca7635b3b34bc4079d14f8f7d98b082dbc0f08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MNCPGMNSYRAK6FE5OX2MVWAWEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved baselines for vision-language pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Romero-Soriano, Enrico Fini, Jakob Verbeek, Michal Drozdzal, Pietro Astolfi","submitted_at":"2023-05-15T14:31:49Z","abstract_excerpt":"Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work claims improvements over CLIP using additional non-contrastive losses inspired from self-supervised learning. However, it is sometimes hard to disentangle the contribution of these additional losses from other implementation details, e.g., data augmentation or regularization techniques, used to train the model. To shed light on this matter, in this paper, we fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08675","kind":"arxiv","version":2},"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/2305.08675/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":"2026-07-05T07:08:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q82gcq7l1nkZc6YviVw/tAFf2L55JamJFkyma8hS6SNqU7l3mq6Y+qo6tG2x9YE0uBlBECLXqsymRrbOLUOFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:37:36.685257Z"},"content_sha256":"0f809cc389f7855a7f6394b8dd50cb64bc1593f464211109bab65cf2d1399a65","schema_version":"1.0","event_id":"sha256:0f809cc389f7855a7f6394b8dd50cb64bc1593f464211109bab65cf2d1399a65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ/bundle.json","state_url":"https://pith.science/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ/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":"2026-07-07T11:37:36Z","links":{"resolver":"https://pith.science/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ","bundle":"https://pith.science/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ/bundle.json","state":"https://pith.science/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNCPGMNSYRAK6FE5OX2MVWAWEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MNCPGMNSYRAK6FE5OX2MVWAWEZ","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":"5ddb0b6ca17660fcc9861e7a22f01d06cd6a4b4ddfa2b9b5e79fb49009082319","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:31:49Z","title_canon_sha256":"5b422b6813dbaae30fdaa69a5fa2a01434e5ae232538957c49b642452ceff9eb"},"schema_version":"1.0","source":{"id":"2305.08675","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08675","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08675v2","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08675","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"MNCPGMNSYRAK","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"pith_short_16","alias_value":"MNCPGMNSYRAK6FE5","created_at":"2026-07-05T07:08:57Z"},{"alias_kind":"pith_short_8","alias_value":"MNCPGMNS","created_at":"2026-07-05T07:08:57Z"}],"graph_snapshots":[{"event_id":"sha256:0f809cc389f7855a7f6394b8dd50cb64bc1593f464211109bab65cf2d1399a65","target":"graph","created_at":"2026-07-05T07:08:57Z","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/2305.08675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work claims improvements over CLIP using additional non-contrastive losses inspired from self-supervised learning. However, it is sometimes hard to disentangle the contribution of these additional losses from other implementation details, e.g., data augmentation or regularization techniques, used to train the model. To shed light on this matter, in this paper, we fi","authors_text":"Adriana Romero-Soriano, Enrico Fini, Jakob Verbeek, Michal Drozdzal, Pietro Astolfi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:31:49Z","title":"Improved baselines for vision-language pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08675","kind":"arxiv","version":2},"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":"sha256:1f575be9ee8232158ef09f07d8ca7635b3b34bc4079d14f8f7d98b082dbc0f08","target":"record","created_at":"2026-07-05T07:08:57Z","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":"5ddb0b6ca17660fcc9861e7a22f01d06cd6a4b4ddfa2b9b5e79fb49009082319","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:31:49Z","title_canon_sha256":"5b422b6813dbaae30fdaa69a5fa2a01434e5ae232538957c49b642452ceff9eb"},"schema_version":"1.0","source":{"id":"2305.08675","kind":"arxiv","version":2}},"canonical_sha256":"6344f331b2c440af149d75f4cad8162641c9041520285e173dabe1c68ead9f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6344f331b2c440af149d75f4cad8162641c9041520285e173dabe1c68ead9f7f","first_computed_at":"2026-07-05T07:08:57.395289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:57.395289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d63OG3hsN0eFnr1yw0DTgpBq35vn/PIB/UEb3ZOWexHtHROMa5MWFzSqbAnFFKyJEqMB4eYK7pwsHxD4t4mSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:57.395837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08675","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f575be9ee8232158ef09f07d8ca7635b3b34bc4079d14f8f7d98b082dbc0f08","sha256:0f809cc389f7855a7f6394b8dd50cb64bc1593f464211109bab65cf2d1399a65"],"state_sha256":"82fa5a933a517da94d16914427823ebd8bb435b956f8f3fa188c45199e7ef158"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"utmY2k8AjYjqG9vBh8GdFsmScbvE6O1Y3MZXYoNIYTHCo3YyLWqD92zS57Mw1/YLw6YziGEfPtc3jeCtSFiCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:37:36.687187Z","bundle_sha256":"22c69ba4797a7decb45c1862f68af39f5be59ec05e2490935184f37d498b3093"}}