{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U7XGBRE4BF2I2PTY5WKT2KRRH4","short_pith_number":"pith:U7XGBRE4","canonical_record":{"source":{"id":"2409.09251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T01:25:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb13ddf032299f8767b190c1c295f56bb073e109f117f10098570d7bb2ee28a8","abstract_canon_sha256":"8adfdc7a376b0d3d069fbd03f7ab85dc7a9977adbf0179e468c1fdceef1e68e2"},"schema_version":"1.0"},"canonical_sha256":"a7ee60c49c09748d3e78ed953d2a313f27b187848b9093b03496e9d6a271bc21","source":{"kind":"arxiv","id":"2409.09251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09251","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09251v1","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09251","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"U7XGBRE4BF2I","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"U7XGBRE4BF2I2PTY","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"U7XGBRE4","created_at":"2026-07-05T09:07:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U7XGBRE4BF2I2PTY5WKT2KRRH4","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T01:25:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb13ddf032299f8767b190c1c295f56bb073e109f117f10098570d7bb2ee28a8","abstract_canon_sha256":"8adfdc7a376b0d3d069fbd03f7ab85dc7a9977adbf0179e468c1fdceef1e68e2"},"schema_version":"1.0"},"canonical_sha256":"a7ee60c49c09748d3e78ed953d2a313f27b187848b9093b03496e9d6a271bc21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:07.013537Z","signature_b64":"ror1x2e8MW+BqY6HxFVMY51yuSB52j1PeVtvG4fghoeiTc+Uy8g9nT5KHRORJeaqcXjBHwhPVNz6oFIZLyrICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ee60c49c09748d3e78ed953d2a313f27b187848b9093b03496e9d6a271bc21","last_reissued_at":"2026-07-05T09:07:07.013081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:07.013081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09251","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":"2026-07-05T09:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7KnmR43ImZHWA4ydco3P7pKq3gEjTUc/gLnj+MOhvChCuxIfrp9BPOyJYn+pzvRZfEIQQM9FRgLbQ74BCkdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:21:07.236330Z"},"content_sha256":"1f64c215a20f4c25d8631ec88530cf23a68cc6b502c0d15896e08e7326ed1a2d","schema_version":"1.0","event_id":"sha256:1f64c215a20f4c25d8631ec88530cf23a68cc6b502c0d15896e08e7326ed1a2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U7XGBRE4BF2I2PTY5WKT2KRRH4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Afshar Shamsi, Ahmadreza Argha, Arash Mohammadi, Ehsan Abbasnejad, Hamid Alinejad-Rokny, Rejisa Becirovic","submitted_at":"2024-09-14T01:25:52Z","abstract_excerpt":"Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence metric, its effectiveness can be limited, particularly in biased scenarios. Extending existing approaches like the Pseudo Label Probability Difference (PLPD), we introduce ETAGE, a refined TTA method that integrates entropy minimization with gradient norms and PLPD, to enhance sample selection and adaptation. Our method prioritizes samples that are less likely to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09251","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/2409.09251/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":"2026-07-05T09:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8GEADnBspX9OnOr3vIQfgvqOFnD3wgfpNIc65Sj/EemK4kiBn46xfGoXzJh7zGahc/ugmgxKl+t73gv+JvZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:21:07.236954Z"},"content_sha256":"43d2aae08b1bc005a44f012060af937efc7c6667efff14f1121e30341b0f26b6","schema_version":"1.0","event_id":"sha256:43d2aae08b1bc005a44f012060af937efc7c6667efff14f1121e30341b0f26b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4/bundle.json","state_url":"https://pith.science/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4/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":"2026-07-07T07:21:07Z","links":{"resolver":"https://pith.science/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4","bundle":"https://pith.science/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4/bundle.json","state":"https://pith.science/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7XGBRE4BF2I2PTY5WKT2KRRH4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U7XGBRE4BF2I2PTY5WKT2KRRH4","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":"8adfdc7a376b0d3d069fbd03f7ab85dc7a9977adbf0179e468c1fdceef1e68e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T01:25:52Z","title_canon_sha256":"cb13ddf032299f8767b190c1c295f56bb073e109f117f10098570d7bb2ee28a8"},"schema_version":"1.0","source":{"id":"2409.09251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09251","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09251v1","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09251","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"U7XGBRE4BF2I","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"U7XGBRE4BF2I2PTY","created_at":"2026-07-05T09:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"U7XGBRE4","created_at":"2026-07-05T09:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:43d2aae08b1bc005a44f012060af937efc7c6667efff14f1121e30341b0f26b6","target":"graph","created_at":"2026-07-05T09:07:07Z","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/2409.09251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditional TTA methods often rely on entropy as a confidence metric, its effectiveness can be limited, particularly in biased scenarios. Extending existing approaches like the Pseudo Label Probability Difference (PLPD), we introduce ETAGE, a refined TTA method that integrates entropy minimization with gradient norms and PLPD, to enhance sample selection and adaptation. Our method prioritizes samples that are less likely to","authors_text":"Afshar Shamsi, Ahmadreza Argha, Arash Mohammadi, Ehsan Abbasnejad, Hamid Alinejad-Rokny, Rejisa Becirovic","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T01:25:52Z","title":"ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09251","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":"sha256:1f64c215a20f4c25d8631ec88530cf23a68cc6b502c0d15896e08e7326ed1a2d","target":"record","created_at":"2026-07-05T09:07:07Z","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":"8adfdc7a376b0d3d069fbd03f7ab85dc7a9977adbf0179e468c1fdceef1e68e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T01:25:52Z","title_canon_sha256":"cb13ddf032299f8767b190c1c295f56bb073e109f117f10098570d7bb2ee28a8"},"schema_version":"1.0","source":{"id":"2409.09251","kind":"arxiv","version":1}},"canonical_sha256":"a7ee60c49c09748d3e78ed953d2a313f27b187848b9093b03496e9d6a271bc21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7ee60c49c09748d3e78ed953d2a313f27b187848b9093b03496e9d6a271bc21","first_computed_at":"2026-07-05T09:07:07.013081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:07.013081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ror1x2e8MW+BqY6HxFVMY51yuSB52j1PeVtvG4fghoeiTc+Uy8g9nT5KHRORJeaqcXjBHwhPVNz6oFIZLyrICg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:07.013537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f64c215a20f4c25d8631ec88530cf23a68cc6b502c0d15896e08e7326ed1a2d","sha256:43d2aae08b1bc005a44f012060af937efc7c6667efff14f1121e30341b0f26b6"],"state_sha256":"9231dec102fd6652527ca0210925c0deedbc28f421c665cfb3d49051a49bd5d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tLbj0imZ1MRx8USWeRYrrmaMSoDEvYAaeAnal+ifceGzoNeRbXcmOHTqGwEd2dJt25+R13+/1LodAsVs5xyzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:21:07.244432Z","bundle_sha256":"1dda9acd612bafaed1b63f5c6de2d93e4e07b3fff12e018e3c7e83839492ba75"}}