{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6I3T4LJ22XG4OPNLPTKKTT4CPG","short_pith_number":"pith:6I3T4LJ2","canonical_record":{"source":{"id":"2401.02137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:42:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e6da194bf6b5b223fe778dae66cd19b0662c55b8a51f14c3e9d99fc328d9d72","abstract_canon_sha256":"8d1fb90edee2a052d94d33f982772505dc500cbfbb39fa1491264defd181e0a9"},"schema_version":"1.0"},"canonical_sha256":"f2373e2d3ad5cdc73dab7cd4a9cf82799f323f2878c7baa907739bdd92dc1e73","source":{"kind":"arxiv","id":"2401.02137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02137","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02137v1","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02137","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"6I3T4LJ22XG4","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"6I3T4LJ22XG4OPNL","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"6I3T4LJ2","created_at":"2026-07-05T07:30:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6I3T4LJ22XG4OPNLPTKKTT4CPG","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:42:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e6da194bf6b5b223fe778dae66cd19b0662c55b8a51f14c3e9d99fc328d9d72","abstract_canon_sha256":"8d1fb90edee2a052d94d33f982772505dc500cbfbb39fa1491264defd181e0a9"},"schema_version":"1.0"},"canonical_sha256":"f2373e2d3ad5cdc73dab7cd4a9cf82799f323f2878c7baa907739bdd92dc1e73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:11.845721Z","signature_b64":"gPau7y68vjjNNtyUpq9Tup+eQRZLLT1LhKfCNF6O4CpyeY7vRA3AT4rg9telMofvt1f5SzATuMrcw3iG+is2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2373e2d3ad5cdc73dab7cd4a9cf82799f323f2878c7baa907739bdd92dc1e73","last_reissued_at":"2026-07-05T07:30:11.845225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:11.845225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02137","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":"2026-07-05T07:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o9e9Q6YD1mPNhNzhPfvVai4qThrVSWGEQDgpQ6ZsA975t19IL6EyPalxlEME3hmzJy4Uz+KVuPFrFvFlbiswDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:43:29.491287Z"},"content_sha256":"e27ac1b12c2ee9429e71f52698c6c4215c28f1173fef3f50f6bb6074e89bfb71","schema_version":"1.0","event_id":"sha256:e27ac1b12c2ee9429e71f52698c6c4215c28f1173fef3f50f6bb6074e89bfb71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6I3T4LJ22XG4OPNLPTKKTT4CPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Furong Xu, Jian Liu, Ming Yang, Qingpei Guo, Ziping Ma","submitted_at":"2024-01-04T08:42:36Z","abstract_excerpt":"Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and Image Caption (IC) into a unified framework, resulting in impressive results. CLIP imposes a bidirectional constraints on global representation of entire images and sentences. Although IC conducts an unidirectional image-to-text generation on local representation, it lacks any constraint on local text-to-image reconstruction, which limits the ability to underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02137","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/2401.02137/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":"2026-07-05T07:30:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"En5PkJ0WIbn8ZcQcyzgimdfIdYMQq9x03DPOYoGhjoQVMRE71nKi+RbkVKbIabHNUEC1vEqeJVzu+jqZHmCxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:43:29.491886Z"},"content_sha256":"6f686f634891673edb8ca4f9ea2b97858cd0153d47e4bbcd1b2f26ba695029d0","schema_version":"1.0","event_id":"sha256:6f686f634891673edb8ca4f9ea2b97858cd0153d47e4bbcd1b2f26ba695029d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG/bundle.json","state_url":"https://pith.science/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG/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":"2026-08-19T05:43:29Z","links":{"resolver":"https://pith.science/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG","bundle":"https://pith.science/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG/bundle.json","state":"https://pith.science/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6I3T4LJ22XG4OPNLPTKKTT4CPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6I3T4LJ22XG4OPNLPTKKTT4CPG","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":"8d1fb90edee2a052d94d33f982772505dc500cbfbb39fa1491264defd181e0a9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:42:36Z","title_canon_sha256":"9e6da194bf6b5b223fe778dae66cd19b0662c55b8a51f14c3e9d99fc328d9d72"},"schema_version":"1.0","source":{"id":"2401.02137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02137","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02137v1","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02137","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_12","alias_value":"6I3T4LJ22XG4","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_16","alias_value":"6I3T4LJ22XG4OPNL","created_at":"2026-07-05T07:30:11Z"},{"alias_kind":"pith_short_8","alias_value":"6I3T4LJ2","created_at":"2026-07-05T07:30:11Z"}],"graph_snapshots":[{"event_id":"sha256:6f686f634891673edb8ca4f9ea2b97858cd0153d47e4bbcd1b2f26ba695029d0","target":"graph","created_at":"2026-07-05T07:30:11Z","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/2401.02137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, integrates Contrastive Language-Image Pretraining (CLIP) and Image Caption (IC) into a unified framework, resulting in impressive results. CLIP imposes a bidirectional constraints on global representation of entire images and sentences. Although IC conducts an unidirectional image-to-text generation on local representation, it lacks any constraint on local text-to-image reconstruction, which limits the ability to underst","authors_text":"Furong Xu, Jian Liu, Ming Yang, Qingpei Guo, Ziping Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:42:36Z","title":"SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02137","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:e27ac1b12c2ee9429e71f52698c6c4215c28f1173fef3f50f6bb6074e89bfb71","target":"record","created_at":"2026-07-05T07:30:11Z","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":"8d1fb90edee2a052d94d33f982772505dc500cbfbb39fa1491264defd181e0a9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T08:42:36Z","title_canon_sha256":"9e6da194bf6b5b223fe778dae66cd19b0662c55b8a51f14c3e9d99fc328d9d72"},"schema_version":"1.0","source":{"id":"2401.02137","kind":"arxiv","version":1}},"canonical_sha256":"f2373e2d3ad5cdc73dab7cd4a9cf82799f323f2878c7baa907739bdd92dc1e73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2373e2d3ad5cdc73dab7cd4a9cf82799f323f2878c7baa907739bdd92dc1e73","first_computed_at":"2026-07-05T07:30:11.845225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:11.845225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gPau7y68vjjNNtyUpq9Tup+eQRZLLT1LhKfCNF6O4CpyeY7vRA3AT4rg9telMofvt1f5SzATuMrcw3iG+is2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:11.845721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e27ac1b12c2ee9429e71f52698c6c4215c28f1173fef3f50f6bb6074e89bfb71","sha256:6f686f634891673edb8ca4f9ea2b97858cd0153d47e4bbcd1b2f26ba695029d0"],"state_sha256":"ecdea7c3a9d9ff830b6c6db062af751bb7f23fa3c9fdbf194910553b9c6ac5eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqc404ukm+oqfJgjtlWY7coVINTfX0SyTPE7mXncjT9DBJTMbfQ5D+mxJJmuyeWgoKEmrAmdxAU1ju6u29zpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:43:29.496596Z","bundle_sha256":"0efff3f02f8ccb35bf7a1b17204ead1a961b160e52510d82b6315cadb027a941"}}