{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3CASNF7HBXQPV7LIWGYERCDGUJ","short_pith_number":"pith:3CASNF7H","canonical_record":{"source":{"id":"2512.02456","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-02T06:30:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3cab414ddfd8e2fcf302420c005102fd97e23d88b1eb1da8b9368c8b74c997fb","abstract_canon_sha256":"e794d9b6eede041f0aede2b0241765e99af14b3d76bd7a507d3d1ace5aab400e"},"schema_version":"1.0"},"canonical_sha256":"d8812697e70de0fafd68b1b0488866a24405705b4a4e58f8e6305b39006ab089","source":{"kind":"arxiv","id":"2512.02456","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02456","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02456v2","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02456","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"3CASNF7HBXQP","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"3CASNF7HBXQPV7LI","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"3CASNF7H","created_at":"2026-06-30T02:17:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3CASNF7HBXQPV7LIWGYERCDGUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2512.02456","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-02T06:30:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3cab414ddfd8e2fcf302420c005102fd97e23d88b1eb1da8b9368c8b74c997fb","abstract_canon_sha256":"e794d9b6eede041f0aede2b0241765e99af14b3d76bd7a507d3d1ace5aab400e"},"schema_version":"1.0"},"canonical_sha256":"d8812697e70de0fafd68b1b0488866a24405705b4a4e58f8e6305b39006ab089","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:12.372043Z","signature_b64":"yTtS1Gy/tnhkWdWFLa0/WTgP7oOxJvwEnoV3RDWYoW3yL3Hqwr8YH/LqRAu42oobOSRUOM9CSNK+Pjn54egaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8812697e70de0fafd68b1b0488866a24405705b4a4e58f8e6305b39006ab089","last_reissued_at":"2026-06-30T02:17:12.371162Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:12.371162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.02456","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":"2026-06-30T02:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nOBOrEK0bpdp6tVyp+h+UZzl2NWjmax1mir0Vb9DLYFILhazIIAoJmRSKs7s3FN2QEVw5/3QAqJC6qVQF8c1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T04:05:17.274663Z"},"content_sha256":"6404bc963557b0c7bd145dbaa2b34a92687f2a420f591fbfa18e8ed9d37826b1","schema_version":"1.0","event_id":"sha256:6404bc963557b0c7bd145dbaa2b34a92687f2a420f591fbfa18e8ed9d37826b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3CASNF7HBXQPV7LIWGYERCDGUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See, Think, Learn: A Self-Taught Multimodal Reasoner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Sadbhawna, Sonam Gupta, Sourabh Sharma","submitted_at":"2025-12-02T06:30:10Z","abstract_excerpt":"Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in either limits the performance of VLMs. Prior efforts to enhance reasoning often depend on high-quality chain-of-thought (CoT) data, obtained via labor-intensive human annotations, costly proprietary models, or self-training methods that overlook perception. To address these limitations, we propose a simple yet effective self-training framework called See-Think"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02456","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/2512.02456/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":"2026-06-30T02:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x7l+5Olu7ZAiEfgqjEXpxeJwAm0Yjn2Pip78o1H/eqBc6QGc7sPjj4tzfra5Wo0zNCQBOwGqI5upfK7cIFHhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T04:05:17.275302Z"},"content_sha256":"a825d9eadc88e1a8bcfa395e9e4abea37f2aea3684da6043106b4f72c5786e64","schema_version":"1.0","event_id":"sha256:a825d9eadc88e1a8bcfa395e9e4abea37f2aea3684da6043106b4f72c5786e64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CASNF7HBXQPV7LIWGYERCDGUJ/bundle.json","state_url":"https://pith.science/pith/3CASNF7HBXQPV7LIWGYERCDGUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CASNF7HBXQPV7LIWGYERCDGUJ/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":"2026-07-02T04:05:17Z","links":{"resolver":"https://pith.science/pith/3CASNF7HBXQPV7LIWGYERCDGUJ","bundle":"https://pith.science/pith/3CASNF7HBXQPV7LIWGYERCDGUJ/bundle.json","state":"https://pith.science/pith/3CASNF7HBXQPV7LIWGYERCDGUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CASNF7HBXQPV7LIWGYERCDGUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3CASNF7HBXQPV7LIWGYERCDGUJ","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":"e794d9b6eede041f0aede2b0241765e99af14b3d76bd7a507d3d1ace5aab400e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-02T06:30:10Z","title_canon_sha256":"3cab414ddfd8e2fcf302420c005102fd97e23d88b1eb1da8b9368c8b74c997fb"},"schema_version":"1.0","source":{"id":"2512.02456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02456","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02456v2","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02456","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"3CASNF7HBXQP","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"3CASNF7HBXQPV7LI","created_at":"2026-06-30T02:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"3CASNF7H","created_at":"2026-06-30T02:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:a825d9eadc88e1a8bcfa395e9e4abea37f2aea3684da6043106b4f72c5786e64","target":"graph","created_at":"2026-06-30T02:17:12Z","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/2512.02456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in either limits the performance of VLMs. Prior efforts to enhance reasoning often depend on high-quality chain-of-thought (CoT) data, obtained via labor-intensive human annotations, costly proprietary models, or self-training methods that overlook perception. To address these limitations, we propose a simple yet effective self-training framework called See-Think","authors_text":"Sadbhawna, Sonam Gupta, Sourabh Sharma","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-02T06:30:10Z","title":"See, Think, Learn: A Self-Taught Multimodal Reasoner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02456","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":"sha256:6404bc963557b0c7bd145dbaa2b34a92687f2a420f591fbfa18e8ed9d37826b1","target":"record","created_at":"2026-06-30T02:17:12Z","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":"e794d9b6eede041f0aede2b0241765e99af14b3d76bd7a507d3d1ace5aab400e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-02T06:30:10Z","title_canon_sha256":"3cab414ddfd8e2fcf302420c005102fd97e23d88b1eb1da8b9368c8b74c997fb"},"schema_version":"1.0","source":{"id":"2512.02456","kind":"arxiv","version":2}},"canonical_sha256":"d8812697e70de0fafd68b1b0488866a24405705b4a4e58f8e6305b39006ab089","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8812697e70de0fafd68b1b0488866a24405705b4a4e58f8e6305b39006ab089","first_computed_at":"2026-06-30T02:17:12.371162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:12.371162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yTtS1Gy/tnhkWdWFLa0/WTgP7oOxJvwEnoV3RDWYoW3yL3Hqwr8YH/LqRAu42oobOSRUOM9CSNK+Pjn54egaDA==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:12.372043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.02456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6404bc963557b0c7bd145dbaa2b34a92687f2a420f591fbfa18e8ed9d37826b1","sha256:a825d9eadc88e1a8bcfa395e9e4abea37f2aea3684da6043106b4f72c5786e64"],"state_sha256":"0aa02bf8ed68e5aee6db13fe099ef847d847dd727cc66ba69fdf976cb5f7503e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dFKUdpgLXUdyniRx5ahbWjmA8ZlWuO3zPDQuB84xmzCCqg3krMBVjQUneX4BON6ypDR7gVc3HN7lIiSZeyIsBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T04:05:17.278575Z","bundle_sha256":"cbf8e3ec1b0050111df1e8633715ab975de8b9d5d371ef030b7664a30e666cbd"}}