{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OUD2UJ4DO7DH7RTUXP5P6HVJNL","short_pith_number":"pith:OUD2UJ4D","canonical_record":{"source":{"id":"2510.15614","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-17T13:00:32Z","cross_cats_sorted":[],"title_canon_sha256":"a0938d4d04253feaf53dc1ca972aa35b17bb159263f6ee2513ff01b0288d0440","abstract_canon_sha256":"601e96f120b14c2f47451bb3df64a8299e8b02003bd4a3acdfc8629a585bbc79"},"schema_version":"1.0"},"canonical_sha256":"7507aa278377c67fc674bbfaff1ea96ace133513325eec2d44dd00c3a83c7bd7","source":{"kind":"arxiv","id":"2510.15614","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.15614","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2510.15614v3","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.15614","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"OUD2UJ4DO7DH","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"OUD2UJ4DO7DH7RTU","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"OUD2UJ4D","created_at":"2026-06-01T01:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OUD2UJ4DO7DH7RTUXP5P6HVJNL","target":"record","payload":{"canonical_record":{"source":{"id":"2510.15614","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-17T13:00:32Z","cross_cats_sorted":[],"title_canon_sha256":"a0938d4d04253feaf53dc1ca972aa35b17bb159263f6ee2513ff01b0288d0440","abstract_canon_sha256":"601e96f120b14c2f47451bb3df64a8299e8b02003bd4a3acdfc8629a585bbc79"},"schema_version":"1.0"},"canonical_sha256":"7507aa278377c67fc674bbfaff1ea96ace133513325eec2d44dd00c3a83c7bd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:23.736648Z","signature_b64":"CNRa/8h8zJNA03rpn5oCSonyVcXGvJgw/UUg+qTXm8UTt0zlEvrd/OQA8H85oK33Y73DoPOKHyDekgEsdK0cAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7507aa278377c67fc674bbfaff1ea96ace133513325eec2d44dd00c3a83c7bd7","last_reissued_at":"2026-06-01T01:02:23.735576Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:23.735576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.15614","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XE6KrRNiSZKdbBiXUDNCQO1pIvOdwPwokadapHSLg/abUaq/m5dxUCjHdu4IOIZruVRZu5jfu6FVkSVoOInVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:54:59.748954Z"},"content_sha256":"7c7aa02f8981b7d5d06d7656d7b8cf13e3f11fe303b8e831792179f08cf722b1","schema_version":"1.0","event_id":"sha256:7c7aa02f8981b7d5d06d7656d7b8cf13e3f11fe303b8e831792179f08cf722b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OUD2UJ4DO7DH7RTUXP5P6HVJNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Goyal, Beibei Lin, Dianbo Liu, Hongyu He, Qiran Zou, Tingting Chen, Yew-Soon Ong, Zifeng Yuan","submitted_at":"2025-10-17T13:00:32Z","abstract_excerpt":"Many scientific problems are underdetermined: multiple distinct hypotheses are equally consistent with the same observations. In such settings, effective inference requires not only producing valid explanations, but also systematically exploring and covering the admissible hypothesis set. We introduce HypoSpace, a benchmark that treats large language models (LLMs) as samplers over finite hypothesis spaces and evaluates them on three metrics: Validity, Uniqueness, and Recovery. HypoSpace spans three structured domains (causal graph inference, gravity-constrained 3D voxel reconstruction, and Boo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.15614","kind":"arxiv","version":3},"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/2510.15614/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":"2026-06-01T01:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2iI0VyS9hv9ZWsqyX/KGRi0Q447eOu9y2Aveaw5s2EXpzEowmtS29UtSb1CFLLikqrJA5dkwmDW7PrEi0vVOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:54:59.749348Z"},"content_sha256":"cfa8a4c8fda99526af81d9441950906b1eb2585fce1a0b14fe53ee5fb78ffb51","schema_version":"1.0","event_id":"sha256:cfa8a4c8fda99526af81d9441950906b1eb2585fce1a0b14fe53ee5fb78ffb51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL/bundle.json","state_url":"https://pith.science/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL/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":"2026-06-02T20:54:59Z","links":{"resolver":"https://pith.science/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL","bundle":"https://pith.science/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL/bundle.json","state":"https://pith.science/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUD2UJ4DO7DH7RTUXP5P6HVJNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OUD2UJ4DO7DH7RTUXP5P6HVJNL","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":"601e96f120b14c2f47451bb3df64a8299e8b02003bd4a3acdfc8629a585bbc79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-17T13:00:32Z","title_canon_sha256":"a0938d4d04253feaf53dc1ca972aa35b17bb159263f6ee2513ff01b0288d0440"},"schema_version":"1.0","source":{"id":"2510.15614","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.15614","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2510.15614v3","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.15614","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"OUD2UJ4DO7DH","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"OUD2UJ4DO7DH7RTU","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"OUD2UJ4D","created_at":"2026-06-01T01:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:cfa8a4c8fda99526af81d9441950906b1eb2585fce1a0b14fe53ee5fb78ffb51","target":"graph","created_at":"2026-06-01T01:02:23Z","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/2510.15614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many scientific problems are underdetermined: multiple distinct hypotheses are equally consistent with the same observations. In such settings, effective inference requires not only producing valid explanations, but also systematically exploring and covering the admissible hypothesis set. We introduce HypoSpace, a benchmark that treats large language models (LLMs) as samplers over finite hypothesis spaces and evaluates them on three metrics: Validity, Uniqueness, and Recovery. HypoSpace spans three structured domains (causal graph inference, gravity-constrained 3D voxel reconstruction, and Boo","authors_text":"Anirudh Goyal, Beibei Lin, Dianbo Liu, Hongyu He, Qiran Zou, Tingting Chen, Yew-Soon Ong, Zifeng Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-17T13:00:32Z","title":"HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.15614","kind":"arxiv","version":3},"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":"sha256:7c7aa02f8981b7d5d06d7656d7b8cf13e3f11fe303b8e831792179f08cf722b1","target":"record","created_at":"2026-06-01T01:02:23Z","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":"601e96f120b14c2f47451bb3df64a8299e8b02003bd4a3acdfc8629a585bbc79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-17T13:00:32Z","title_canon_sha256":"a0938d4d04253feaf53dc1ca972aa35b17bb159263f6ee2513ff01b0288d0440"},"schema_version":"1.0","source":{"id":"2510.15614","kind":"arxiv","version":3}},"canonical_sha256":"7507aa278377c67fc674bbfaff1ea96ace133513325eec2d44dd00c3a83c7bd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7507aa278377c67fc674bbfaff1ea96ace133513325eec2d44dd00c3a83c7bd7","first_computed_at":"2026-06-01T01:02:23.735576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:23.735576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CNRa/8h8zJNA03rpn5oCSonyVcXGvJgw/UUg+qTXm8UTt0zlEvrd/OQA8H85oK33Y73DoPOKHyDekgEsdK0cAg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:23.736648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.15614","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c7aa02f8981b7d5d06d7656d7b8cf13e3f11fe303b8e831792179f08cf722b1","sha256:cfa8a4c8fda99526af81d9441950906b1eb2585fce1a0b14fe53ee5fb78ffb51"],"state_sha256":"68c5eb8861cafa443d9ac54e1fd90efce854adf3629b284493e9b127e9a5cf09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sor1HXkFCg7i80h9qWRjP0iPijaRT4MIyr2G+W2bwEmj7aI9yepZ88YYePljzS5SRyD8DL0Njk7qV9RxW2I3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:54:59.751497Z","bundle_sha256":"ecbfb3886215fe58d8b7c68f8ab9355ca22a1cf2407e3da1726efb106c16a6d8"}}