{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EI4GEAZLVX25R4PYS4LIVT4LVL","short_pith_number":"pith:EI4GEAZL","canonical_record":{"source":{"id":"2407.21654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T14:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"51471baee9680156986c7c5eda785d6fb72b19a15d6838186363e3f74243ab58","abstract_canon_sha256":"d83c8abfece12a08f0d4ad21ee3816293673a476cb56c9701070a88ddb5c0d6c"},"schema_version":"1.0"},"canonical_sha256":"223862032badf5d8f1f897168acf8baac355184b392a521480516f26697b552b","source":{"kind":"arxiv","id":"2407.21654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21654","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21654v1","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21654","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"pith_short_12","alias_value":"EI4GEAZLVX25","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"pith_short_16","alias_value":"EI4GEAZLVX25R4PY","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"pith_short_8","alias_value":"EI4GEAZL","created_at":"2026-07-05T08:50:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EI4GEAZLVX25R4PYS4LIVT4LVL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T14:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"51471baee9680156986c7c5eda785d6fb72b19a15d6838186363e3f74243ab58","abstract_canon_sha256":"d83c8abfece12a08f0d4ad21ee3816293673a476cb56c9701070a88ddb5c0d6c"},"schema_version":"1.0"},"canonical_sha256":"223862032badf5d8f1f897168acf8baac355184b392a521480516f26697b552b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:41.998389Z","signature_b64":"KOfLjC1XqZPQUrjZLOq1KTzmaUllH+rjjK1HH1ibNAOg5vWrG0JKWp+q+MoPP7ypDV/C5zBDHRFLgbIldXW/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"223862032badf5d8f1f897168acf8baac355184b392a521480516f26697b552b","last_reissued_at":"2026-07-05T08:50:41.997988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:41.997988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21654","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":"2026-07-05T08:50:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBX+Qe/M0tKY6YrTUjrKSlzgVycWN04MvmTaoD1yZgyUBrpoyBKNjLmF8t9WZyyTecxiO6sBXnAKxocfX8r8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:35:43.998912Z"},"content_sha256":"821e579ad567b31d8810f85a58bf236e853f393e7a2d2b4c31efd409fabf4be0","schema_version":"1.0","event_id":"sha256:821e579ad567b31d8810f85a58bf236e853f393e7a2d2b4c31efd409fabf4be0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EI4GEAZLVX25R4PYS4LIVT4LVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Das, Bernt Schiele, Li Jiang, Xinting Hu","submitted_at":"2024-07-31T14:56:42Z","abstract_excerpt":"Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image features from CLIP, resulting in class ambiguities along boundaries. Moreover, the global scene representations in CLIP text embeddings do not directly correlate with the local and detailed pixel-level features, making meaningful alignment more difficult. To address these limitations, we introduce MTA-CLIP, a novel framework employing mask-level vision-langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21654","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/2407.21654/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":"2026-07-05T08:50:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOUs+nj5VzgKXQYZbeKO+OFL/G96Vi06tiPAqmJNyaOsDl+82fQWOwKtcGRmGsK4uDCoVGz+73kmMXp0PlZjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:35:43.999814Z"},"content_sha256":"5e3124892542cf60e56ab666bbb5ff990e6ca0557229c1056fd4cfecb42c10e3","schema_version":"1.0","event_id":"sha256:5e3124892542cf60e56ab666bbb5ff990e6ca0557229c1056fd4cfecb42c10e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EI4GEAZLVX25R4PYS4LIVT4LVL/bundle.json","state_url":"https://pith.science/pith/EI4GEAZLVX25R4PYS4LIVT4LVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EI4GEAZLVX25R4PYS4LIVT4LVL/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":"2026-08-23T12:35:44Z","links":{"resolver":"https://pith.science/pith/EI4GEAZLVX25R4PYS4LIVT4LVL","bundle":"https://pith.science/pith/EI4GEAZLVX25R4PYS4LIVT4LVL/bundle.json","state":"https://pith.science/pith/EI4GEAZLVX25R4PYS4LIVT4LVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EI4GEAZLVX25R4PYS4LIVT4LVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EI4GEAZLVX25R4PYS4LIVT4LVL","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":"d83c8abfece12a08f0d4ad21ee3816293673a476cb56c9701070a88ddb5c0d6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T14:56:42Z","title_canon_sha256":"51471baee9680156986c7c5eda785d6fb72b19a15d6838186363e3f74243ab58"},"schema_version":"1.0","source":{"id":"2407.21654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21654","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21654v1","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21654","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"pith_short_12","alias_value":"EI4GEAZLVX25","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"pith_short_16","alias_value":"EI4GEAZLVX25R4PY","created_at":"2026-07-05T08:50:41Z"},{"alias_kind":"pith_short_8","alias_value":"EI4GEAZL","created_at":"2026-07-05T08:50:41Z"}],"graph_snapshots":[{"event_id":"sha256:5e3124892542cf60e56ab666bbb5ff990e6ca0557229c1056fd4cfecb42c10e3","target":"graph","created_at":"2026-07-05T08:50:41Z","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/2407.21654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image features from CLIP, resulting in class ambiguities along boundaries. Moreover, the global scene representations in CLIP text embeddings do not directly correlate with the local and detailed pixel-level features, making meaningful alignment more difficult. To address these limitations, we introduce MTA-CLIP, a novel framework employing mask-level vision-langua","authors_text":"Anurag Das, Bernt Schiele, Li Jiang, Xinting Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T14:56:42Z","title":"MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21654","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":"sha256:821e579ad567b31d8810f85a58bf236e853f393e7a2d2b4c31efd409fabf4be0","target":"record","created_at":"2026-07-05T08:50:41Z","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":"d83c8abfece12a08f0d4ad21ee3816293673a476cb56c9701070a88ddb5c0d6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T14:56:42Z","title_canon_sha256":"51471baee9680156986c7c5eda785d6fb72b19a15d6838186363e3f74243ab58"},"schema_version":"1.0","source":{"id":"2407.21654","kind":"arxiv","version":1}},"canonical_sha256":"223862032badf5d8f1f897168acf8baac355184b392a521480516f26697b552b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"223862032badf5d8f1f897168acf8baac355184b392a521480516f26697b552b","first_computed_at":"2026-07-05T08:50:41.997988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:41.997988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KOfLjC1XqZPQUrjZLOq1KTzmaUllH+rjjK1HH1ibNAOg5vWrG0JKWp+q+MoPP7ypDV/C5zBDHRFLgbIldXW/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:41.998389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:821e579ad567b31d8810f85a58bf236e853f393e7a2d2b4c31efd409fabf4be0","sha256:5e3124892542cf60e56ab666bbb5ff990e6ca0557229c1056fd4cfecb42c10e3"],"state_sha256":"adfbfa7d9d8324419a9cacdb2f1f5f8da2dfb32abc8cbce18310bb0eff0ff7a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVpFUllmuk/zVOAWF4RcdA1teJo7H81Q3B8NfXU03yiNxCVSZOvr4UpAHnlwlEGCLxZyN/QSzeujB5aMR5iyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:35:44.006320Z","bundle_sha256":"fecb0ef92595d2278d39a2f089f288c43d46bd78d25a74451271fbf0ce8fabe4"}}