{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MWTBULRBCSQNDRLZVN5ELLYIE5","short_pith_number":"pith:MWTBULRB","canonical_record":{"source":{"id":"2403.06952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:35:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"70b2984c534a150c010ee00e545fbc583b19ce1aff3562ff822b909b6f7060d6","abstract_canon_sha256":"7a8d9f71cf6a2052f760cd949742bc8eafe047d9a55ffbaaed07e3c5fefc7020"},"schema_version":"1.0"},"canonical_sha256":"65a61a2e2114a0d1c579ab7a45af082754fb2cd9ccbbfcebf90efa84c1024e25","source":{"kind":"arxiv","id":"2403.06952","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06952","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06952v1","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06952","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"pith_short_12","alias_value":"MWTBULRBCSQN","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"pith_short_16","alias_value":"MWTBULRBCSQNDRLZ","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"pith_short_8","alias_value":"MWTBULRB","created_at":"2026-07-05T07:54:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MWTBULRBCSQNDRLZVN5ELLYIE5","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:35:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"70b2984c534a150c010ee00e545fbc583b19ce1aff3562ff822b909b6f7060d6","abstract_canon_sha256":"7a8d9f71cf6a2052f760cd949742bc8eafe047d9a55ffbaaed07e3c5fefc7020"},"schema_version":"1.0"},"canonical_sha256":"65a61a2e2114a0d1c579ab7a45af082754fb2cd9ccbbfcebf90efa84c1024e25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:44.934457Z","signature_b64":"H4QpFaOJVv0v8BUAb/cfp89CxkpJP2uV4qdmVKjkMwaF9HHwIGRyPAU5GnM44GdNTIV4uBlVjc9UYFe7hS0zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65a61a2e2114a0d1c579ab7a45af082754fb2cd9ccbbfcebf90efa84c1024e25","last_reissued_at":"2026-07-05T07:54:44.933972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:44.933972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06952","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":"2026-07-05T07:54:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7J0wNQG1KIoqZsgRP3UbpmN6t+KNpUgPdWGgudkCMeuEi/C/TGTfk8iYh7mWBwQauTj1lKWx1+2kSz1+tb4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:33:13.747435Z"},"content_sha256":"82a062bd9b6f894ff91724a4bb25ee086b1bd35a658efb62a217987440ed16f2","schema_version":"1.0","event_id":"sha256:82a062bd9b6f894ff91724a4bb25ee086b1bd35a658efb62a217987440ed16f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MWTBULRBCSQNDRLZVN5ELLYIE5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaehong Yoon, Jaemin Cho, Jialu Li, Mohit Bansal, Yi-Lin Sung","submitted_at":"2024-03-11T17:35:33Z","abstract_excerpt":"Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions. However, these T2I generation models often fall short of generating images that precisely match the details of the text inputs, such as incorrect spatial relationship or missing objects. In this paper, we introduce SELMA: Skill-Specific Expert Learning and Merging with Auto-Generated Data, a novel paradigm to improve the faithfulness of T2I models by fine-tuning models on automatically generated, multi-skill image-text datasets, with skill-specific expert learning a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06952","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/2403.06952/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":"2026-07-05T07:54:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPlz2liY/u5QKlDT6nLkPxYQqTPi3CywiEzDM7/nPpFgCOyZIvBYgUI7eHZoyefqN9+h7xg+DJVX2PL9eLCeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:33:13.748358Z"},"content_sha256":"b156effef212d3f9372361213dd6f11fe010ae9dbd85947300ecd70c1aac1f00","schema_version":"1.0","event_id":"sha256:b156effef212d3f9372361213dd6f11fe010ae9dbd85947300ecd70c1aac1f00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWTBULRBCSQNDRLZVN5ELLYIE5/bundle.json","state_url":"https://pith.science/pith/MWTBULRBCSQNDRLZVN5ELLYIE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWTBULRBCSQNDRLZVN5ELLYIE5/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":"2026-08-17T21:33:13Z","links":{"resolver":"https://pith.science/pith/MWTBULRBCSQNDRLZVN5ELLYIE5","bundle":"https://pith.science/pith/MWTBULRBCSQNDRLZVN5ELLYIE5/bundle.json","state":"https://pith.science/pith/MWTBULRBCSQNDRLZVN5ELLYIE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWTBULRBCSQNDRLZVN5ELLYIE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MWTBULRBCSQNDRLZVN5ELLYIE5","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":"7a8d9f71cf6a2052f760cd949742bc8eafe047d9a55ffbaaed07e3c5fefc7020","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:35:33Z","title_canon_sha256":"70b2984c534a150c010ee00e545fbc583b19ce1aff3562ff822b909b6f7060d6"},"schema_version":"1.0","source":{"id":"2403.06952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06952","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06952v1","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06952","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"pith_short_12","alias_value":"MWTBULRBCSQN","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"pith_short_16","alias_value":"MWTBULRBCSQNDRLZ","created_at":"2026-07-05T07:54:44Z"},{"alias_kind":"pith_short_8","alias_value":"MWTBULRB","created_at":"2026-07-05T07:54:44Z"}],"graph_snapshots":[{"event_id":"sha256:b156effef212d3f9372361213dd6f11fe010ae9dbd85947300ecd70c1aac1f00","target":"graph","created_at":"2026-07-05T07:54:44Z","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/2403.06952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions. However, these T2I generation models often fall short of generating images that precisely match the details of the text inputs, such as incorrect spatial relationship or missing objects. In this paper, we introduce SELMA: Skill-Specific Expert Learning and Merging with Auto-Generated Data, a novel paradigm to improve the faithfulness of T2I models by fine-tuning models on automatically generated, multi-skill image-text datasets, with skill-specific expert learning a","authors_text":"Jaehong Yoon, Jaemin Cho, Jialu Li, Mohit Bansal, Yi-Lin Sung","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:35:33Z","title":"SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06952","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":"sha256:82a062bd9b6f894ff91724a4bb25ee086b1bd35a658efb62a217987440ed16f2","target":"record","created_at":"2026-07-05T07:54:44Z","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":"7a8d9f71cf6a2052f760cd949742bc8eafe047d9a55ffbaaed07e3c5fefc7020","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:35:33Z","title_canon_sha256":"70b2984c534a150c010ee00e545fbc583b19ce1aff3562ff822b909b6f7060d6"},"schema_version":"1.0","source":{"id":"2403.06952","kind":"arxiv","version":1}},"canonical_sha256":"65a61a2e2114a0d1c579ab7a45af082754fb2cd9ccbbfcebf90efa84c1024e25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65a61a2e2114a0d1c579ab7a45af082754fb2cd9ccbbfcebf90efa84c1024e25","first_computed_at":"2026-07-05T07:54:44.933972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:44.933972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H4QpFaOJVv0v8BUAb/cfp89CxkpJP2uV4qdmVKjkMwaF9HHwIGRyPAU5GnM44GdNTIV4uBlVjc9UYFe7hS0zAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:44.934457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82a062bd9b6f894ff91724a4bb25ee086b1bd35a658efb62a217987440ed16f2","sha256:b156effef212d3f9372361213dd6f11fe010ae9dbd85947300ecd70c1aac1f00"],"state_sha256":"36fd0ad863d2887220d2581c5474379714ca8686813f30ed267d886650135db8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kr4fQz0NGtXL0Mna0EbBhHoxDFtaT4b4a9DqMf6SYPyQJKYAqbumkK/FhoSgVO/JeEtOPp9zb/VGx+zwJqeIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:33:13.799871Z","bundle_sha256":"37da873bc74b060ccf75a7554e781b1c38c2331f81bd1200c41c7c352c32db1b"}}