{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MZHWVXUZSDASXGOWKQH55GDROL","short_pith_number":"pith:MZHWVXUZ","canonical_record":{"source":{"id":"2302.03432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T12:36:35Z","cross_cats_sorted":[],"title_canon_sha256":"6de1dca8ecd619579b792d9767ca237659549fc3101b2f491e51c4a9d1320de5","abstract_canon_sha256":"f13f2397e13d446ea1a13f05947ab4cf243dcb7e2dd697b4b33f411c4c6c8f81"},"schema_version":"1.0"},"canonical_sha256":"664f6ade9990c12b99d6540fde987172fee8e0c8b1f278a8e01d0e20451e526b","source":{"kind":"arxiv","id":"2302.03432","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03432","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03432v1","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03432","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"MZHWVXUZSDAS","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"pith_short_16","alias_value":"MZHWVXUZSDASXGOW","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"pith_short_8","alias_value":"MZHWVXUZ","created_at":"2026-07-05T05:39:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MZHWVXUZSDASXGOWKQH55GDROL","target":"record","payload":{"canonical_record":{"source":{"id":"2302.03432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T12:36:35Z","cross_cats_sorted":[],"title_canon_sha256":"6de1dca8ecd619579b792d9767ca237659549fc3101b2f491e51c4a9d1320de5","abstract_canon_sha256":"f13f2397e13d446ea1a13f05947ab4cf243dcb7e2dd697b4b33f411c4c6c8f81"},"schema_version":"1.0"},"canonical_sha256":"664f6ade9990c12b99d6540fde987172fee8e0c8b1f278a8e01d0e20451e526b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:37.071695Z","signature_b64":"gXP9M4pTZy8U0nGVnt1vbGRm0MsRdpJEsCvYETVLvNN8vu+ZGO6r1qZXczD/d52G0xkldz0ifCb/jtaZrTdvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664f6ade9990c12b99d6540fde987172fee8e0c8b1f278a8e01d0e20451e526b","last_reissued_at":"2026-07-05T05:39:37.071272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:37.071272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.03432","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":"2026-07-05T05:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZuKY9jfOFPcL3ItWEY7b2J17Y07HNIM8AENUwNYoSZ/uEVqMNszHlwBQaMNbMC3D9CF/j3lDsD/OBuobXsUKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:34:48.493955Z"},"content_sha256":"82cadc9e8ecc0965ca0ba8bf70a29368e531315121d5c51b4c1847b9865debde","schema_version":"1.0","event_id":"sha256:82cadc9e8ecc0965ca0ba8bf70a29368e531315121d5c51b4c1847b9865debde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MZHWVXUZSDASXGOWKQH55GDROL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimCon Loss with Multiple Views for Text Supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"R. Manmatha, Srikar Appalaraju, Yash Patel, Yi Zhu, Yusheng Xie","submitted_at":"2023-02-07T12:36:35Z","abstract_excerpt":"Learning to segment images purely by relying on the image-text alignment from web data can lead to sub-optimal performance due to noise in the data. The noise comes from the samples where the associated text does not correlate with the image's visual content. Instead of purely relying on the alignment from the noisy data, this paper proposes a novel loss function termed SimCon, which accounts for intra-modal similarities to determine the appropriate set of positive samples to align. Further, using multiple views of the image (created synthetically) for training and combining the SimCon loss wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03432","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/2302.03432/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":"2026-07-05T05:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HwsCEmaR/fNO5GmKNAq3GwNCORU2fI2xktRhQqWI4Fu8KR6Dc5zLM+8yeguIVnftJ2ccmX6NKOZd64NDdFSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:34:48.494518Z"},"content_sha256":"9221aa6fa89b2c04e32f5562e190cafa2c5352ce67dc76daf881a47c7b0ddc1e","schema_version":"1.0","event_id":"sha256:9221aa6fa89b2c04e32f5562e190cafa2c5352ce67dc76daf881a47c7b0ddc1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MZHWVXUZSDASXGOWKQH55GDROL/bundle.json","state_url":"https://pith.science/pith/MZHWVXUZSDASXGOWKQH55GDROL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MZHWVXUZSDASXGOWKQH55GDROL/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":"2026-08-14T08:34:48Z","links":{"resolver":"https://pith.science/pith/MZHWVXUZSDASXGOWKQH55GDROL","bundle":"https://pith.science/pith/MZHWVXUZSDASXGOWKQH55GDROL/bundle.json","state":"https://pith.science/pith/MZHWVXUZSDASXGOWKQH55GDROL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MZHWVXUZSDASXGOWKQH55GDROL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MZHWVXUZSDASXGOWKQH55GDROL","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":"f13f2397e13d446ea1a13f05947ab4cf243dcb7e2dd697b4b33f411c4c6c8f81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T12:36:35Z","title_canon_sha256":"6de1dca8ecd619579b792d9767ca237659549fc3101b2f491e51c4a9d1320de5"},"schema_version":"1.0","source":{"id":"2302.03432","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03432","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03432v1","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03432","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"MZHWVXUZSDAS","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"pith_short_16","alias_value":"MZHWVXUZSDASXGOW","created_at":"2026-07-05T05:39:37Z"},{"alias_kind":"pith_short_8","alias_value":"MZHWVXUZ","created_at":"2026-07-05T05:39:37Z"}],"graph_snapshots":[{"event_id":"sha256:9221aa6fa89b2c04e32f5562e190cafa2c5352ce67dc76daf881a47c7b0ddc1e","target":"graph","created_at":"2026-07-05T05:39:37Z","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/2302.03432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to segment images purely by relying on the image-text alignment from web data can lead to sub-optimal performance due to noise in the data. The noise comes from the samples where the associated text does not correlate with the image's visual content. Instead of purely relying on the alignment from the noisy data, this paper proposes a novel loss function termed SimCon, which accounts for intra-modal similarities to determine the appropriate set of positive samples to align. Further, using multiple views of the image (created synthetically) for training and combining the SimCon loss wi","authors_text":"R. Manmatha, Srikar Appalaraju, Yash Patel, Yi Zhu, Yusheng Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T12:36:35Z","title":"SimCon Loss with Multiple Views for Text Supervised Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03432","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":"sha256:82cadc9e8ecc0965ca0ba8bf70a29368e531315121d5c51b4c1847b9865debde","target":"record","created_at":"2026-07-05T05:39:37Z","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":"f13f2397e13d446ea1a13f05947ab4cf243dcb7e2dd697b4b33f411c4c6c8f81","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T12:36:35Z","title_canon_sha256":"6de1dca8ecd619579b792d9767ca237659549fc3101b2f491e51c4a9d1320de5"},"schema_version":"1.0","source":{"id":"2302.03432","kind":"arxiv","version":1}},"canonical_sha256":"664f6ade9990c12b99d6540fde987172fee8e0c8b1f278a8e01d0e20451e526b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"664f6ade9990c12b99d6540fde987172fee8e0c8b1f278a8e01d0e20451e526b","first_computed_at":"2026-07-05T05:39:37.071272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:37.071272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gXP9M4pTZy8U0nGVnt1vbGRm0MsRdpJEsCvYETVLvNN8vu+ZGO6r1qZXczD/d52G0xkldz0ifCb/jtaZrTdvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:37.071695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03432","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82cadc9e8ecc0965ca0ba8bf70a29368e531315121d5c51b4c1847b9865debde","sha256:9221aa6fa89b2c04e32f5562e190cafa2c5352ce67dc76daf881a47c7b0ddc1e"],"state_sha256":"a44a2ef2fd91d6c85bbd0707036ee08ed25c4fa0f16ccef81805b809e466f5ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gA14ItAXwblynFXK6Wjg4lMF+qKIX01YAk/ZZRQM1E/7UCWMXb+HHthfHqALpT1tj4KKhy5TngiBi2fpg24Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:34:48.499804Z","bundle_sha256":"43ee953c6c41ac3ccd3ffa2a92c6827696987bc8e18de07bb4a5bcb4278a235e"}}