{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JIUHOO2U6AJI3IIXLA72QNJSF2","short_pith_number":"pith:JIUHOO2U","canonical_record":{"source":{"id":"2501.16718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T05:50:54Z","cross_cats_sorted":[],"title_canon_sha256":"0ae39eb2ae7a3505ef50b5cfa9282c1d0e90b867d635cda7e2d227183f8305c9","abstract_canon_sha256":"8f628aca80977e0a95a9b67466a0bfb6a11395e2ec3103f456e13f969a5d3d72"},"schema_version":"1.0"},"canonical_sha256":"4a28773b54f0128da117583fa835322ea8c49755b91a0e179fafcd13c69aec45","source":{"kind":"arxiv","id":"2501.16718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16718","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16718v2","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16718","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"JIUHOO2U6AJI","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"JIUHOO2U6AJI3IIX","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"JIUHOO2U","created_at":"2026-07-05T10:09:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JIUHOO2U6AJI3IIXLA72QNJSF2","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T05:50:54Z","cross_cats_sorted":[],"title_canon_sha256":"0ae39eb2ae7a3505ef50b5cfa9282c1d0e90b867d635cda7e2d227183f8305c9","abstract_canon_sha256":"8f628aca80977e0a95a9b67466a0bfb6a11395e2ec3103f456e13f969a5d3d72"},"schema_version":"1.0"},"canonical_sha256":"4a28773b54f0128da117583fa835322ea8c49755b91a0e179fafcd13c69aec45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:52.307655Z","signature_b64":"HD6NWgh0NC5pCFCZ7BnxXcIBVDiGhclnxxXDqTuRfHtxUvDXlSZ9mo1B5aj/thBv+GHwjNyzot/AXK1pLYloCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a28773b54f0128da117583fa835322ea8c49755b91a0e179fafcd13c69aec45","last_reissued_at":"2026-07-05T10:09:52.307248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:52.307248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16718","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bCbVbgBGrrW1tOBv8fbotsyLFsMuxRdt4Ne6TVJt69dt8qrbRtV66/PbexSqWw5gouzuEYckVJI4xk8Up/+VDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:35:14.006165Z"},"content_sha256":"5e268e9d186a2baf6c0d08cf9e6e49032862c3cc55d99f817adeb05673f26b99","schema_version":"1.0","event_id":"sha256:5e268e9d186a2baf6c0d08cf9e6e49032862c3cc55d99f817adeb05673f26b99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JIUHOO2U6AJI3IIXLA72QNJSF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hengzhuang Li, Teng Zhang","submitted_at":"2025-01-28T05:50:54Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16718","kind":"arxiv","version":2},"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/2501.16718/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":"2026-07-05T10:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5XXogimSzFH2/VRgojWsCiFnpv/Xym/Rl7+muneif6oE7aoP0xIFeB+Z/QZ97de6HlRWyGW4ne5C76/BlF3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:35:14.006545Z"},"content_sha256":"12478d90f2c02cab135c87b97fd9bad4ade57d259b5656f1bf93803e9710df1d","schema_version":"1.0","event_id":"sha256:12478d90f2c02cab135c87b97fd9bad4ade57d259b5656f1bf93803e9710df1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JIUHOO2U6AJI3IIXLA72QNJSF2/bundle.json","state_url":"https://pith.science/pith/JIUHOO2U6AJI3IIXLA72QNJSF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JIUHOO2U6AJI3IIXLA72QNJSF2/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":"2026-08-12T22:35:14Z","links":{"resolver":"https://pith.science/pith/JIUHOO2U6AJI3IIXLA72QNJSF2","bundle":"https://pith.science/pith/JIUHOO2U6AJI3IIXLA72QNJSF2/bundle.json","state":"https://pith.science/pith/JIUHOO2U6AJI3IIXLA72QNJSF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JIUHOO2U6AJI3IIXLA72QNJSF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JIUHOO2U6AJI3IIXLA72QNJSF2","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":"8f628aca80977e0a95a9b67466a0bfb6a11395e2ec3103f456e13f969a5d3d72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T05:50:54Z","title_canon_sha256":"0ae39eb2ae7a3505ef50b5cfa9282c1d0e90b867d635cda7e2d227183f8305c9"},"schema_version":"1.0","source":{"id":"2501.16718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16718","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16718v2","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16718","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"JIUHOO2U6AJI","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"JIUHOO2U6AJI3IIX","created_at":"2026-07-05T10:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"JIUHOO2U","created_at":"2026-07-05T10:09:52Z"}],"graph_snapshots":[{"event_id":"sha256:12478d90f2c02cab135c87b97fd9bad4ade57d259b5656f1bf93803e9710df1d","target":"graph","created_at":"2026-07-05T10:09:52Z","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/2501.16718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing ","authors_text":"Hengzhuang Li, Teng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T05:50:54Z","title":"Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16718","kind":"arxiv","version":2},"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":"sha256:5e268e9d186a2baf6c0d08cf9e6e49032862c3cc55d99f817adeb05673f26b99","target":"record","created_at":"2026-07-05T10:09:52Z","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":"8f628aca80977e0a95a9b67466a0bfb6a11395e2ec3103f456e13f969a5d3d72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T05:50:54Z","title_canon_sha256":"0ae39eb2ae7a3505ef50b5cfa9282c1d0e90b867d635cda7e2d227183f8305c9"},"schema_version":"1.0","source":{"id":"2501.16718","kind":"arxiv","version":2}},"canonical_sha256":"4a28773b54f0128da117583fa835322ea8c49755b91a0e179fafcd13c69aec45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a28773b54f0128da117583fa835322ea8c49755b91a0e179fafcd13c69aec45","first_computed_at":"2026-07-05T10:09:52.307248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:52.307248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HD6NWgh0NC5pCFCZ7BnxXcIBVDiGhclnxxXDqTuRfHtxUvDXlSZ9mo1B5aj/thBv+GHwjNyzot/AXK1pLYloCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:52.307655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e268e9d186a2baf6c0d08cf9e6e49032862c3cc55d99f817adeb05673f26b99","sha256:12478d90f2c02cab135c87b97fd9bad4ade57d259b5656f1bf93803e9710df1d"],"state_sha256":"0d7e2be12b5cad0ce34dec274550a4ba9a1204e29be508b08882ffb5f447b51e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNwaIOPEz3/Ifz+fSbIcmMwrz5w4Z88SvlIsAANP/y0ibuCQit/wU6SgkTw7s+BG7q59vaZbvBQjuW7sPGfeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:35:14.009264Z","bundle_sha256":"73e98a8839b8dc00b5aa590fc97a9e18a594cd15066450f8943fcb97f7fa3ec3"}}