{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CVVYJATEYKKOT6HC5NNVCNYOFM","short_pith_number":"pith:CVVYJATE","canonical_record":{"source":{"id":"2412.15396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T20:58:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"95b15bd72345de541994cace0723310b55e79acefde2cfa9a823418e7fa75e51","abstract_canon_sha256":"0f15a9ace5618d830fd2d4792dbcdcb9f85545366b92342e2f733e1c6cae3948"},"schema_version":"1.0"},"canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","source":{"kind":"arxiv","id":"2412.15396","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15396","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15396v2","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15396","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"CVVYJATEYKKO","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"pith_short_16","alias_value":"CVVYJATEYKKOT6HC","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"pith_short_8","alias_value":"CVVYJATE","created_at":"2026-07-05T10:44:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CVVYJATEYKKOT6HC5NNVCNYOFM","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T20:58:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"95b15bd72345de541994cace0723310b55e79acefde2cfa9a823418e7fa75e51","abstract_canon_sha256":"0f15a9ace5618d830fd2d4792dbcdcb9f85545366b92342e2f733e1c6cae3948"},"schema_version":"1.0"},"canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:21.026011Z","signature_b64":"oZVrDhiisOwLQ7mFuVy3QQIXb/LBUXeTDKpuO76ccWyPd20yBY4FWNNjaPcLQOqBtMpKIVFV3jNnBzqK7tzeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","last_reissued_at":"2026-07-05T10:44:21.025522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:21.025522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15396","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":"2026-07-05T10:44:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpGHSg48DHVBW3Cx/SwCW49Tk05t1+5As2I9yIwlLCCtVZC5ZA4d8p1SgDE0EjrMCggm+XXdV+uZ1DWp4kxuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:53:41.187870Z"},"content_sha256":"03b9037c440bfe141f80ea916e8a6c060bc55be79ff5964169b643cf3fab2a79","schema_version":"1.0","event_id":"sha256:03b9037c440bfe141f80ea916e8a6c060bc55be79ff5964169b643cf3fab2a79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CVVYJATEYKKOT6HC5NNVCNYOFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Visual Composition through Improved Semantic Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Abhijit Ogale, Austin Stone, Bingyi Cao, Hagen Soltau, Jonathon Shlens, Kaifeng Chen, Robert Geirhos, Xi Yi, Ye Xia","submitted_at":"2024-12-19T20:58:26Z","abstract_excerpt":"Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building better representations for a small number of discrete objects bereft of an understanding of how these objects are interacting. One can observe this limitation in representations learned through captions or contrastive learning -- where the learned model treats an image essentially as a bag of words. Several works have attempted to address this limitation through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15396","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/2412.15396/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":"2026-07-05T10:44:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xfVfJaawfFfsd+6uTyWTnPi77YmLQiXcG2LQFDWBjj36yz+z8oR/E2Eh23gTjk2XEtGKs6cOXc31mUT/nl8tCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:53:41.188246Z"},"content_sha256":"3f3c389abb6195580479f898751f2764680e2c56714a8d50787fb485c44f5103","schema_version":"1.0","event_id":"sha256:3f3c389abb6195580479f898751f2764680e2c56714a8d50787fb485c44f5103"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/bundle.json","state_url":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/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":"2026-07-07T14:53:41Z","links":{"resolver":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM","bundle":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/bundle.json","state":"https://pith.science/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CVVYJATEYKKOT6HC5NNVCNYOFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CVVYJATEYKKOT6HC5NNVCNYOFM","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":"0f15a9ace5618d830fd2d4792dbcdcb9f85545366b92342e2f733e1c6cae3948","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T20:58:26Z","title_canon_sha256":"95b15bd72345de541994cace0723310b55e79acefde2cfa9a823418e7fa75e51"},"schema_version":"1.0","source":{"id":"2412.15396","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15396","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15396v2","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15396","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"pith_short_12","alias_value":"CVVYJATEYKKO","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"pith_short_16","alias_value":"CVVYJATEYKKOT6HC","created_at":"2026-07-05T10:44:21Z"},{"alias_kind":"pith_short_8","alias_value":"CVVYJATE","created_at":"2026-07-05T10:44:21Z"}],"graph_snapshots":[{"event_id":"sha256:3f3c389abb6195580479f898751f2764680e2c56714a8d50787fb485c44f5103","target":"graph","created_at":"2026-07-05T10:44:21Z","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/2412.15396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building better representations for a small number of discrete objects bereft of an understanding of how these objects are interacting. One can observe this limitation in representations learned through captions or contrastive learning -- where the learned model treats an image essentially as a bag of words. Several works have attempted to address this limitation through ","authors_text":"Abhijit Ogale, Austin Stone, Bingyi Cao, Hagen Soltau, Jonathon Shlens, Kaifeng Chen, Robert Geirhos, Xi Yi, Ye Xia","cross_cats":["cs.AI","cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T20:58:26Z","title":"Learning Visual Composition through Improved Semantic Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15396","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":"sha256:03b9037c440bfe141f80ea916e8a6c060bc55be79ff5964169b643cf3fab2a79","target":"record","created_at":"2026-07-05T10:44:21Z","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":"0f15a9ace5618d830fd2d4792dbcdcb9f85545366b92342e2f733e1c6cae3948","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T20:58:26Z","title_canon_sha256":"95b15bd72345de541994cace0723310b55e79acefde2cfa9a823418e7fa75e51"},"schema_version":"1.0","source":{"id":"2412.15396","kind":"arxiv","version":2}},"canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"156b848264c294e9f8e2eb5b51370e2b17ede9bfa86567bc6fdc83208f555fb7","first_computed_at":"2026-07-05T10:44:21.025522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:21.025522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oZVrDhiisOwLQ7mFuVy3QQIXb/LBUXeTDKpuO76ccWyPd20yBY4FWNNjaPcLQOqBtMpKIVFV3jNnBzqK7tzeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:21.026011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15396","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03b9037c440bfe141f80ea916e8a6c060bc55be79ff5964169b643cf3fab2a79","sha256:3f3c389abb6195580479f898751f2764680e2c56714a8d50787fb485c44f5103"],"state_sha256":"1379f2808747824b0e30f85d08146fd8d110c56422d3e1f08bead64b734f2507"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUmT2XbSKoH4jsE3GS0wxRI3bKPwjRkSNSdlyTXJH5RywR9IsTBXlIHdAuuoz+uPJSn3MzQGgqAuhk+PqMwkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:53:41.190102Z","bundle_sha256":"40b0d8df9abf9aaa34b48f8417f30181dbb74edfd8083d8a4f518015389f842f"}}