{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4QX3JA3Y6TB5UOD3IDWBR42KXJ","short_pith_number":"pith:4QX3JA3Y","canonical_record":{"source":{"id":"2312.08366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"8d11246093c1532de9450582245b6c8783ca2cd935921cb1b1b1d9834bda2d35","abstract_canon_sha256":"e4ab3bfcdb8856e961aeff3db727bf2ed8f28799be2dfa560bac1b3e9e794296"},"schema_version":"1.0"},"canonical_sha256":"e42fb48378f4c3da387b40ec18f34aba58995886305d027feb62becc52dd4176","source":{"kind":"arxiv","id":"2312.08366","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08366","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08366v1","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08366","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"pith_short_12","alias_value":"4QX3JA3Y6TB5","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"pith_short_16","alias_value":"4QX3JA3Y6TB5UOD3","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"pith_short_8","alias_value":"4QX3JA3Y","created_at":"2026-07-05T07:23:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4QX3JA3Y6TB5UOD3IDWBR42KXJ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"8d11246093c1532de9450582245b6c8783ca2cd935921cb1b1b1d9834bda2d35","abstract_canon_sha256":"e4ab3bfcdb8856e961aeff3db727bf2ed8f28799be2dfa560bac1b3e9e794296"},"schema_version":"1.0"},"canonical_sha256":"e42fb48378f4c3da387b40ec18f34aba58995886305d027feb62becc52dd4176","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:52.475214Z","signature_b64":"Bbl65ij+XvF7mOnb2EUmtg/EknGkwTqN4n7FNu26IZnkCc6wu0orac/fIkcqhJfXxh7JZJGvoXHSYHkjptQfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e42fb48378f4c3da387b40ec18f34aba58995886305d027feb62becc52dd4176","last_reissued_at":"2026-07-05T07:23:52.474807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:52.474807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08366","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":"2026-07-05T07:23:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kmod2RgsQwMsuYtcBHH1kNg+qV3lC8uiYRsc/XFum/l5w6C7r58iQLhw7Sv7fLl9+uHXkfAfIHfsO1CLDNyPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:55:04.329692Z"},"content_sha256":"b1b029e04908509b172c960b718c6a7aacc9d9efceb4bc4d800edd1f91222124","schema_version":"1.0","event_id":"sha256:b1b029e04908509b172c960b718c6a7aacc9d9efceb4bc4d800edd1f91222124"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4QX3JA3Y6TB5UOD3IDWBR42KXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See, Say, and Segment: Teaching LMMs to Overcome False Premises","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Chan, Giscard Biamby, Joseph E. Gonzalez, Lisa Dunlap, Ritwik Gupta, Trevor Darrell, Tsung-Han Wu, Xudong Wang","submitted_at":"2023-12-13T18:58:04Z","abstract_excerpt":"Current open-source Large Multimodal Models (LMMs) excel at tasks such as open-vocabulary language grounding and segmentation but can suffer under false premises when queries imply the existence of something that is not actually present in the image. We observe that existing methods that fine-tune an LMM to segment images significantly degrade their ability to reliably determine (\"see\") if an object is present and to interact naturally with humans (\"say\"), a form of catastrophic forgetting. In this work, we propose a cascading and joint training approach for LMMs to solve this task, avoiding c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08366","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/2312.08366/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":"2026-07-05T07:23:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mczvTHQM7EL4VdTwofzrpuBEw9Yd/YzSao7msy7NwvuZiyXCAAMFuhoA5GbfDSqRmw3jtSDedGnv3ZGB/z2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:55:04.330210Z"},"content_sha256":"424e4af1f38ce9674c1ed964c5c14b11bd3af6e566c820f9aa5b92463585a844","schema_version":"1.0","event_id":"sha256:424e4af1f38ce9674c1ed964c5c14b11bd3af6e566c820f9aa5b92463585a844"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ/bundle.json","state_url":"https://pith.science/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ/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":"2026-08-20T21:55:04Z","links":{"resolver":"https://pith.science/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ","bundle":"https://pith.science/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ/bundle.json","state":"https://pith.science/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QX3JA3Y6TB5UOD3IDWBR42KXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4QX3JA3Y6TB5UOD3IDWBR42KXJ","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":"e4ab3bfcdb8856e961aeff3db727bf2ed8f28799be2dfa560bac1b3e9e794296","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:04Z","title_canon_sha256":"8d11246093c1532de9450582245b6c8783ca2cd935921cb1b1b1d9834bda2d35"},"schema_version":"1.0","source":{"id":"2312.08366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08366","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08366v1","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08366","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"pith_short_12","alias_value":"4QX3JA3Y6TB5","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"pith_short_16","alias_value":"4QX3JA3Y6TB5UOD3","created_at":"2026-07-05T07:23:52Z"},{"alias_kind":"pith_short_8","alias_value":"4QX3JA3Y","created_at":"2026-07-05T07:23:52Z"}],"graph_snapshots":[{"event_id":"sha256:424e4af1f38ce9674c1ed964c5c14b11bd3af6e566c820f9aa5b92463585a844","target":"graph","created_at":"2026-07-05T07:23:52Z","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/2312.08366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current open-source Large Multimodal Models (LMMs) excel at tasks such as open-vocabulary language grounding and segmentation but can suffer under false premises when queries imply the existence of something that is not actually present in the image. We observe that existing methods that fine-tune an LMM to segment images significantly degrade their ability to reliably determine (\"see\") if an object is present and to interact naturally with humans (\"say\"), a form of catastrophic forgetting. In this work, we propose a cascading and joint training approach for LMMs to solve this task, avoiding c","authors_text":"David Chan, Giscard Biamby, Joseph E. Gonzalez, Lisa Dunlap, Ritwik Gupta, Trevor Darrell, Tsung-Han Wu, Xudong Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:04Z","title":"See, Say, and Segment: Teaching LMMs to Overcome False Premises"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08366","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:b1b029e04908509b172c960b718c6a7aacc9d9efceb4bc4d800edd1f91222124","target":"record","created_at":"2026-07-05T07:23:52Z","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":"e4ab3bfcdb8856e961aeff3db727bf2ed8f28799be2dfa560bac1b3e9e794296","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T18:58:04Z","title_canon_sha256":"8d11246093c1532de9450582245b6c8783ca2cd935921cb1b1b1d9834bda2d35"},"schema_version":"1.0","source":{"id":"2312.08366","kind":"arxiv","version":1}},"canonical_sha256":"e42fb48378f4c3da387b40ec18f34aba58995886305d027feb62becc52dd4176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e42fb48378f4c3da387b40ec18f34aba58995886305d027feb62becc52dd4176","first_computed_at":"2026-07-05T07:23:52.474807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:52.474807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bbl65ij+XvF7mOnb2EUmtg/EknGkwTqN4n7FNu26IZnkCc6wu0orac/fIkcqhJfXxh7JZJGvoXHSYHkjptQfCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:52.475214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1b029e04908509b172c960b718c6a7aacc9d9efceb4bc4d800edd1f91222124","sha256:424e4af1f38ce9674c1ed964c5c14b11bd3af6e566c820f9aa5b92463585a844"],"state_sha256":"4b16e83aa8cb6d20e4d51aa71fc267ba2c01c29caf494acaefdcf3f5daee8369"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ous+7sad/otCv6FSK3hlMhX7MMo5fXfm83DkoKqTaQQ2jF8edH8mJQEqieIIUQV+GwqdF7lGhYnyr9/dcMZiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:55:04.335023Z","bundle_sha256":"d6085311558c3a07aaa283de4ee47e146f3db90a4a1a85c17614c64269a1bc66"}}