{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IVY2WW6WFBOEBS75FEPAZO6IZD","short_pith_number":"pith:IVY2WW6W","canonical_record":{"source":{"id":"2505.23604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T16:15:36Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"d1b089fa856f8fbfd4c19481ca8b614b03fc4ecd0f7eb3f3edf740c0995a1bc8","abstract_canon_sha256":"e64c86a9fa04c632931b0e3b3b88225f30816d178867db120473f77eeb210603"},"schema_version":"1.0"},"canonical_sha256":"4571ab5bd6285c40cbfd291e0cbbc8c8dcfeeb2901e05fa9d9eb4d2a71393dd9","source":{"kind":"arxiv","id":"2505.23604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23604","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23604v1","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23604","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"pith_short_12","alias_value":"IVY2WW6WFBOE","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"pith_short_16","alias_value":"IVY2WW6WFBOEBS75","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"pith_short_8","alias_value":"IVY2WW6W","created_at":"2026-07-05T11:12:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IVY2WW6WFBOEBS75FEPAZO6IZD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T16:15:36Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"d1b089fa856f8fbfd4c19481ca8b614b03fc4ecd0f7eb3f3edf740c0995a1bc8","abstract_canon_sha256":"e64c86a9fa04c632931b0e3b3b88225f30816d178867db120473f77eeb210603"},"schema_version":"1.0"},"canonical_sha256":"4571ab5bd6285c40cbfd291e0cbbc8c8dcfeeb2901e05fa9d9eb4d2a71393dd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:04.506630Z","signature_b64":"2LkTo2v3zfvSykcmx0hTkdBPmyseCE0Xq2WH3oUFqYPdW7yIQzYK3tdGToFRJuH3KOJ3rzQd0t9NllbiXnb7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4571ab5bd6285c40cbfd291e0cbbc8c8dcfeeb2901e05fa9d9eb4d2a71393dd9","last_reissued_at":"2026-07-05T11:12:04.506158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:04.506158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23604","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":"2026-07-05T11:12:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnmfzUS6MVBotlMt8RBfGiI4+enWF16QfaFGI0r1lI1a1DKgZXMMHB5cBumkA81KzcG1Ocf++iO0gVD95pheBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:55:38.221919Z"},"content_sha256":"27e0b0883717e6e14daabaf1f774ca0b1baec8cff4f46ebfe340dea2fbcd4bc3","schema_version":"1.0","event_id":"sha256:27e0b0883717e6e14daabaf1f774ca0b1baec8cff4f46ebfe340dea2fbcd4bc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IVY2WW6WFBOEBS75FEPAZO6IZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Chuang Gan, Dan Gutfreund, David Cox, Delin Chen, Gregory Wornell, Guangtao Zeng, Maohao Shen, Subhro Das, Wei Lu, Zhang-Wei Hong, Zhenting Qi","submitted_at":"2025-05-29T16:15:36Z","abstract_excerpt":"Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especially when model parameters are less than 100B. While smaller models are preferable in practice due to their lower computational cost, improving their performance remains challenging. Existing approaches primarily rely on supervised fine-tuning (SFT) with high-quality data, which is expensive to curate at scale. An alternative is test-time scaling: generating multiple outputs, scoring them using a verifier, and selecting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23604","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/2505.23604/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":"2026-07-05T11:12:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eRpd9mQQVM3lXKQpGtTpid6JQZE+UHWWp0ls5RZkCnmWtkfwQeZgG3lwRJ1JlLkFoyughOK99QT5r35YeufcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:55:38.222585Z"},"content_sha256":"bbaf8b750455fd88feb620f3cb28924b2a99413dd5e2d2e331eae7dfca0f20df","schema_version":"1.0","event_id":"sha256:bbaf8b750455fd88feb620f3cb28924b2a99413dd5e2d2e331eae7dfca0f20df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVY2WW6WFBOEBS75FEPAZO6IZD/bundle.json","state_url":"https://pith.science/pith/IVY2WW6WFBOEBS75FEPAZO6IZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVY2WW6WFBOEBS75FEPAZO6IZD/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":"2026-07-07T04:55:38Z","links":{"resolver":"https://pith.science/pith/IVY2WW6WFBOEBS75FEPAZO6IZD","bundle":"https://pith.science/pith/IVY2WW6WFBOEBS75FEPAZO6IZD/bundle.json","state":"https://pith.science/pith/IVY2WW6WFBOEBS75FEPAZO6IZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVY2WW6WFBOEBS75FEPAZO6IZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IVY2WW6WFBOEBS75FEPAZO6IZD","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":"e64c86a9fa04c632931b0e3b3b88225f30816d178867db120473f77eeb210603","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T16:15:36Z","title_canon_sha256":"d1b089fa856f8fbfd4c19481ca8b614b03fc4ecd0f7eb3f3edf740c0995a1bc8"},"schema_version":"1.0","source":{"id":"2505.23604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23604","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23604v1","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23604","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"pith_short_12","alias_value":"IVY2WW6WFBOE","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"pith_short_16","alias_value":"IVY2WW6WFBOEBS75","created_at":"2026-07-05T11:12:04Z"},{"alias_kind":"pith_short_8","alias_value":"IVY2WW6W","created_at":"2026-07-05T11:12:04Z"}],"graph_snapshots":[{"event_id":"sha256:bbaf8b750455fd88feb620f3cb28924b2a99413dd5e2d2e331eae7dfca0f20df","target":"graph","created_at":"2026-07-05T11:12:04Z","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/2505.23604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) perform well on standardized coding benchmarks but struggle with real-world software engineering tasks such as resolving GitHub issues in SWE-Bench, especially when model parameters are less than 100B. While smaller models are preferable in practice due to their lower computational cost, improving their performance remains challenging. Existing approaches primarily rely on supervised fine-tuning (SFT) with high-quality data, which is expensive to curate at scale. An alternative is test-time scaling: generating multiple outputs, scoring them using a verifier, and selecting","authors_text":"Chuang Gan, Dan Gutfreund, David Cox, Delin Chen, Gregory Wornell, Guangtao Zeng, Maohao Shen, Subhro Das, Wei Lu, Zhang-Wei Hong, Zhenting Qi","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T16:15:36Z","title":"Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23604","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":"sha256:27e0b0883717e6e14daabaf1f774ca0b1baec8cff4f46ebfe340dea2fbcd4bc3","target":"record","created_at":"2026-07-05T11:12:04Z","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":"e64c86a9fa04c632931b0e3b3b88225f30816d178867db120473f77eeb210603","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T16:15:36Z","title_canon_sha256":"d1b089fa856f8fbfd4c19481ca8b614b03fc4ecd0f7eb3f3edf740c0995a1bc8"},"schema_version":"1.0","source":{"id":"2505.23604","kind":"arxiv","version":1}},"canonical_sha256":"4571ab5bd6285c40cbfd291e0cbbc8c8dcfeeb2901e05fa9d9eb4d2a71393dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4571ab5bd6285c40cbfd291e0cbbc8c8dcfeeb2901e05fa9d9eb4d2a71393dd9","first_computed_at":"2026-07-05T11:12:04.506158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:04.506158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2LkTo2v3zfvSykcmx0hTkdBPmyseCE0Xq2WH3oUFqYPdW7yIQzYK3tdGToFRJuH3KOJ3rzQd0t9NllbiXnb7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:04.506630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27e0b0883717e6e14daabaf1f774ca0b1baec8cff4f46ebfe340dea2fbcd4bc3","sha256:bbaf8b750455fd88feb620f3cb28924b2a99413dd5e2d2e331eae7dfca0f20df"],"state_sha256":"1ed5a437c741b33311a5871ad0a578cf063f6f1b3bc72955e9a723568a83042b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5qs1PE19wcMft78pcE0sJAOUL44bWDZ8rqtSreWwTHM19LSWK+3z7eg4QCcD83gcbhcpORVqGY1mSnCh7VMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:55:38.225816Z","bundle_sha256":"ffadc8392d0d0feba801b1814e610ecb0933e05bfdd07a7c999a7436e2f8d30f"}}