{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ECWZJFWLTB2OMGV3KPFRSCAL4S","short_pith_number":"pith:ECWZJFWL","schema_version":"1.0","canonical_sha256":"20ad9496cb9874e61abb53cb19080be48088eadc29ceb446b97e00cd769fb27f","source":{"kind":"arxiv","id":"2606.08850","version":1},"attestation_state":"computed","paper":{"title":"Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akash Srivastava, Anna C. Doris, Faez Ahmed, Giorgio Giannone, Kai Xu, Mustafa Eyceoz, Shabana Baig, Shivchander Sudalairaj","submitted_at":"2026-06-07T21:43:37Z","abstract_excerpt":"Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection. However, extending ITS to tasks prone to systematic failure - driven by faulty initial assumptions or unmet multidimensional constraints - typically relies on costly external solvers or brittle, model-based verifiers. Our key insight is that the intrinsic statistics of parallel sample sets, specifically length-adjusted tail entropy, provide a robust discriminative signal for solution quality without access to ground truth. Crucially, these s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.08850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T21:43:37Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"06960986af1d83a5b35546fde14619b4136ec688ba7197d0c3fec3444202b5eb","abstract_canon_sha256":"7d1c0436a7bba0a6ef0235b3ad03260eadf82bbe802b5a7e8bf3b5d4dbd5b6b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:42.848424Z","signature_b64":"53b7wZtUjC172dwhcYIfkYoB19aNOhM6140jcqsLFBd8bSCxO0t22DgGJPbASU9ea+y7mOR0DCGtRh39f5/EAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20ad9496cb9874e61abb53cb19080be48088eadc29ceb446b97e00cd769fb27f","last_reissued_at":"2026-06-09T02:07:42.847598Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:42.847598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akash Srivastava, Anna C. Doris, Faez Ahmed, Giorgio Giannone, Kai Xu, Mustafa Eyceoz, Shabana Baig, Shivchander Sudalairaj","submitted_at":"2026-06-07T21:43:37Z","abstract_excerpt":"Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection. However, extending ITS to tasks prone to systematic failure - driven by faulty initial assumptions or unmet multidimensional constraints - typically relies on costly external solvers or brittle, model-based verifiers. Our key insight is that the intrinsic statistics of parallel sample sets, specifically length-adjusted tail entropy, provide a robust discriminative signal for solution quality without access to ground truth. Crucially, these s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08850","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/2606.08850/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.08850","created_at":"2026-06-09T02:07:42.847706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08850v1","created_at":"2026-06-09T02:07:42.847706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08850","created_at":"2026-06-09T02:07:42.847706+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECWZJFWLTB2O","created_at":"2026-06-09T02:07:42.847706+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECWZJFWLTB2OMGV3","created_at":"2026-06-09T02:07:42.847706+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECWZJFWL","created_at":"2026-06-09T02:07:42.847706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S","json":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S.json","graph_json":"https://pith.science/api/pith-number/ECWZJFWLTB2OMGV3KPFRSCAL4S/graph.json","events_json":"https://pith.science/api/pith-number/ECWZJFWLTB2OMGV3KPFRSCAL4S/events.json","paper":"https://pith.science/paper/ECWZJFWL"},"agent_actions":{"view_html":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S","download_json":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S.json","view_paper":"https://pith.science/paper/ECWZJFWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08850&json=true","fetch_graph":"https://pith.science/api/pith-number/ECWZJFWLTB2OMGV3KPFRSCAL4S/graph.json","fetch_events":"https://pith.science/api/pith-number/ECWZJFWLTB2OMGV3KPFRSCAL4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S/action/storage_attestation","attest_author":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S/action/author_attestation","sign_citation":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S/action/citation_signature","submit_replication":"https://pith.science/pith/ECWZJFWLTB2OMGV3KPFRSCAL4S/action/replication_record"}},"created_at":"2026-06-09T02:07:42.847706+00:00","updated_at":"2026-06-09T02:07:42.847706+00:00"}