{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B2MOI6FZLOH3PPLYJEV6GQHSDH","short_pith_number":"pith:B2MOI6FZ","canonical_record":{"source":{"id":"2311.07877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-14T03:13:47Z","cross_cats_sorted":[],"title_canon_sha256":"40db280c8113cc5ec0460d733f35a11973baf58b376f6f89ccba1bf6f7a7f6e7","abstract_canon_sha256":"7f5ca2d80a5cbc1fe84c46ee829c42d6960334b7a0155effe7eaf46a5f36605e"},"schema_version":"1.0"},"canonical_sha256":"0e98e478b95b8fb7bd78492be340f219c751d97ae5b954a3962c6627bad57dd9","source":{"kind":"arxiv","id":"2311.07877","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07877","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07877v1","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07877","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"B2MOI6FZLOH3","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"pith_short_16","alias_value":"B2MOI6FZLOH3PPLY","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"pith_short_8","alias_value":"B2MOI6FZ","created_at":"2026-07-05T07:12:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B2MOI6FZLOH3PPLYJEV6GQHSDH","target":"record","payload":{"canonical_record":{"source":{"id":"2311.07877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-14T03:13:47Z","cross_cats_sorted":[],"title_canon_sha256":"40db280c8113cc5ec0460d733f35a11973baf58b376f6f89ccba1bf6f7a7f6e7","abstract_canon_sha256":"7f5ca2d80a5cbc1fe84c46ee829c42d6960334b7a0155effe7eaf46a5f36605e"},"schema_version":"1.0"},"canonical_sha256":"0e98e478b95b8fb7bd78492be340f219c751d97ae5b954a3962c6627bad57dd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:25.199671Z","signature_b64":"WtHl4p3iJO0H6Yo3hqkj3DL0D1y39bfQnyXJLMlcgkRAc76phDAXKQuWX87G0yqOlUF0iks/yZuEU13bhM+PCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e98e478b95b8fb7bd78492be340f219c751d97ae5b954a3962c6627bad57dd9","last_reissued_at":"2026-07-05T07:12:25.199251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:25.199251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.07877","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":"2026-07-05T07:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UK2sRNU8wB98w1BS1BeUz4tjFZGfVXpwfjqIzbDgeV4eOsElux0B0F7d618IcBcM/qCf6KypTUKjRf8un9U2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:20:52.949292Z"},"content_sha256":"408f37f629e3ed0aa0062e65ccea1a5a6643ab955fd23f58f127a29a766801d4","schema_version":"1.0","event_id":"sha256:408f37f629e3ed0aa0062e65ccea1a5a6643ab955fd23f58f127a29a766801d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B2MOI6FZLOH3PPLYJEV6GQHSDH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-Time Training for Semantic Segmentation with Output Contrastive Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglu Zhu, Lin Yang, Sunyi Zheng, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui","submitted_at":"2023-11-14T03:13:47Z","abstract_excerpt":"Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge. To improve the model's generalization ability to the new domain during evaluation, the test-time training (TTT) is a challenging paradigm that adapts the source-pretrained model in an online fashion. Early efforts on TTT mainly focus on the image classification task. Directly extending these methods to semantic segmentation easily experiences unstable adaption due to segmentation's inherent characteristics, such as extre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07877","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/2311.07877/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":"2026-07-05T07:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNH1/XFF7oFxwRy/dAbIEMJXxPtax3ft4swpAnBohK5x8vLvGxSmDcHrdE7k9jvMk5xN8T0KiH2WCaxp/pDAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:20:52.949881Z"},"content_sha256":"3fa444fa054e41e82f93bb22473a0187f48a106e012c001bd75d01bf2c3d4052","schema_version":"1.0","event_id":"sha256:3fa444fa054e41e82f93bb22473a0187f48a106e012c001bd75d01bf2c3d4052"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH/bundle.json","state_url":"https://pith.science/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH/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":"2026-08-04T10:20:52Z","links":{"resolver":"https://pith.science/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH","bundle":"https://pith.science/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH/bundle.json","state":"https://pith.science/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2MOI6FZLOH3PPLYJEV6GQHSDH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B2MOI6FZLOH3PPLYJEV6GQHSDH","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":"7f5ca2d80a5cbc1fe84c46ee829c42d6960334b7a0155effe7eaf46a5f36605e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-14T03:13:47Z","title_canon_sha256":"40db280c8113cc5ec0460d733f35a11973baf58b376f6f89ccba1bf6f7a7f6e7"},"schema_version":"1.0","source":{"id":"2311.07877","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07877","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07877v1","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07877","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"B2MOI6FZLOH3","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"pith_short_16","alias_value":"B2MOI6FZLOH3PPLY","created_at":"2026-07-05T07:12:25Z"},{"alias_kind":"pith_short_8","alias_value":"B2MOI6FZ","created_at":"2026-07-05T07:12:25Z"}],"graph_snapshots":[{"event_id":"sha256:3fa444fa054e41e82f93bb22473a0187f48a106e012c001bd75d01bf2c3d4052","target":"graph","created_at":"2026-07-05T07:12:25Z","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/2311.07877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge. To improve the model's generalization ability to the new domain during evaluation, the test-time training (TTT) is a challenging paradigm that adapts the source-pretrained model in an online fashion. Early efforts on TTT mainly focus on the image classification task. Directly extending these methods to semantic segmentation easily experiences unstable adaption due to segmentation's inherent characteristics, such as extre","authors_text":"Chenglu Zhu, Lin Yang, Sunyi Zheng, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-14T03:13:47Z","title":"Test-Time Training for Semantic Segmentation with Output Contrastive Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07877","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":"sha256:408f37f629e3ed0aa0062e65ccea1a5a6643ab955fd23f58f127a29a766801d4","target":"record","created_at":"2026-07-05T07:12:25Z","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":"7f5ca2d80a5cbc1fe84c46ee829c42d6960334b7a0155effe7eaf46a5f36605e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-14T03:13:47Z","title_canon_sha256":"40db280c8113cc5ec0460d733f35a11973baf58b376f6f89ccba1bf6f7a7f6e7"},"schema_version":"1.0","source":{"id":"2311.07877","kind":"arxiv","version":1}},"canonical_sha256":"0e98e478b95b8fb7bd78492be340f219c751d97ae5b954a3962c6627bad57dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e98e478b95b8fb7bd78492be340f219c751d97ae5b954a3962c6627bad57dd9","first_computed_at":"2026-07-05T07:12:25.199251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:25.199251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WtHl4p3iJO0H6Yo3hqkj3DL0D1y39bfQnyXJLMlcgkRAc76phDAXKQuWX87G0yqOlUF0iks/yZuEU13bhM+PCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:25.199671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07877","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:408f37f629e3ed0aa0062e65ccea1a5a6643ab955fd23f58f127a29a766801d4","sha256:3fa444fa054e41e82f93bb22473a0187f48a106e012c001bd75d01bf2c3d4052"],"state_sha256":"79780b8822ed9db8db03a71ae1f3c6dcd67241781a8355fb0852d5aea61bafdd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TW5NzLDdsWEI/dpGcbHr+1PbAvefMYNJz2bGJ2Q648U9dDuOlwyhl9E46PN+YSBCIJpCglAZPLbdOBYXEgKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:20:52.954049Z","bundle_sha256":"af27bec5bc07f8d6a4941fb862bfb306c94a030973f703531a6aaf09476996ab"}}