{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BQ7KLMSH3FR7PV6WXIPM2KP5MY","short_pith_number":"pith:BQ7KLMSH","canonical_record":{"source":{"id":"2502.11775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T13:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"234a898386135bf4d90a32fc112e43cbfb02d349de532557bc95f4184c04c581","abstract_canon_sha256":"45e1edeb9d191e0f007f6ed1ec078baf02ca2b318a68c5c7f168546b533177ee"},"schema_version":"1.0"},"canonical_sha256":"0c3ea5b247d963f7d7d6ba1ecd29fd6634f92f50bee23945ea5138a07fd4a4af","source":{"kind":"arxiv","id":"2502.11775","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11775","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11775v1","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11775","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"BQ7KLMSH3FR7","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"BQ7KLMSH3FR7PV6W","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"BQ7KLMSH","created_at":"2026-07-05T10:15:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BQ7KLMSH3FR7PV6WXIPM2KP5MY","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T13:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"234a898386135bf4d90a32fc112e43cbfb02d349de532557bc95f4184c04c581","abstract_canon_sha256":"45e1edeb9d191e0f007f6ed1ec078baf02ca2b318a68c5c7f168546b533177ee"},"schema_version":"1.0"},"canonical_sha256":"0c3ea5b247d963f7d7d6ba1ecd29fd6634f92f50bee23945ea5138a07fd4a4af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:34.036418Z","signature_b64":"w2ciTpFKyolxOzpqRdeswkOTtH1fwjv8jP3VQ3fSDSAJlsto3hPEeKEPD43fv7wCqAnkPgCPsPS2DraOavA3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c3ea5b247d963f7d7d6ba1ecd29fd6634f92f50bee23945ea5138a07fd4a4af","last_reissued_at":"2026-07-05T10:15:34.035899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:34.035899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11775","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":"2026-07-05T10:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/S0X0XyaKhrBj5cj0sLA9+Ej2IQG3ezbLgCzLKD5dPdDbYl7/TCPspKKeC3Lh1xHwKCQ0rKb/mUZbjL5TeNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:10:29.417170Z"},"content_sha256":"39fbdca9691a243fee59e6e23821db558c6c3429e9f4328400b0f5eb8938229d","schema_version":"1.0","event_id":"sha256:39fbdca9691a243fee59e6e23821db558c6c3429e9f4328400b0f5eb8938229d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BQ7KLMSH3FR7PV6WXIPM2KP5MY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jimin Zhuang, Wei Li, Yixuan Li, Yudong Yang, Zejun Ma","submitted_at":"2025-02-17T13:07:40Z","abstract_excerpt":"While recent advancements in reasoning optimization have significantly enhanced the capabilities of large language models (LLMs), existing efforts to improve reasoning have been limited to solving mathematical problems and focusing on visual graphical inputs, neglecting broader applications in general video understanding.This paper proposes video-SALMONN-o1, the first open-source reasoning-enhanced audio-visual LLM designed for general video understanding tasks. To enhance its reasoning abilities, we develop a reasoning-intensive dataset featuring challenging audio-visual questions with step-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11775","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/2502.11775/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":"2026-07-05T10:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VUMyeBHNiswZLNALUtg37rT6dLZ3/4R+Sit0BLmNE3GlMJweeG3HpI4djPB+Lk0T4PLYmeGrRSdLUFVqlkNICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:10:29.417688Z"},"content_sha256":"c4c7768a53df1a69a3ce933b60f6ba37e4cbbdabc0cc1c103a6612d30e11dcf6","schema_version":"1.0","event_id":"sha256:c4c7768a53df1a69a3ce933b60f6ba37e4cbbdabc0cc1c103a6612d30e11dcf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY/bundle.json","state_url":"https://pith.science/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY/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":"2026-08-10T17:10:29Z","links":{"resolver":"https://pith.science/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY","bundle":"https://pith.science/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY/bundle.json","state":"https://pith.science/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQ7KLMSH3FR7PV6WXIPM2KP5MY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BQ7KLMSH3FR7PV6WXIPM2KP5MY","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":"45e1edeb9d191e0f007f6ed1ec078baf02ca2b318a68c5c7f168546b533177ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T13:07:40Z","title_canon_sha256":"234a898386135bf4d90a32fc112e43cbfb02d349de532557bc95f4184c04c581"},"schema_version":"1.0","source":{"id":"2502.11775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11775","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11775v1","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11775","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"BQ7KLMSH3FR7","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"BQ7KLMSH3FR7PV6W","created_at":"2026-07-05T10:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"BQ7KLMSH","created_at":"2026-07-05T10:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:c4c7768a53df1a69a3ce933b60f6ba37e4cbbdabc0cc1c103a6612d30e11dcf6","target":"graph","created_at":"2026-07-05T10:15:34Z","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/2502.11775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent advancements in reasoning optimization have significantly enhanced the capabilities of large language models (LLMs), existing efforts to improve reasoning have been limited to solving mathematical problems and focusing on visual graphical inputs, neglecting broader applications in general video understanding.This paper proposes video-SALMONN-o1, the first open-source reasoning-enhanced audio-visual LLM designed for general video understanding tasks. To enhance its reasoning abilities, we develop a reasoning-intensive dataset featuring challenging audio-visual questions with step-b","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jimin Zhuang, Wei Li, Yixuan Li, Yudong Yang, Zejun Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T13:07:40Z","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11775","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":"sha256:39fbdca9691a243fee59e6e23821db558c6c3429e9f4328400b0f5eb8938229d","target":"record","created_at":"2026-07-05T10:15:34Z","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":"45e1edeb9d191e0f007f6ed1ec078baf02ca2b318a68c5c7f168546b533177ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-17T13:07:40Z","title_canon_sha256":"234a898386135bf4d90a32fc112e43cbfb02d349de532557bc95f4184c04c581"},"schema_version":"1.0","source":{"id":"2502.11775","kind":"arxiv","version":1}},"canonical_sha256":"0c3ea5b247d963f7d7d6ba1ecd29fd6634f92f50bee23945ea5138a07fd4a4af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c3ea5b247d963f7d7d6ba1ecd29fd6634f92f50bee23945ea5138a07fd4a4af","first_computed_at":"2026-07-05T10:15:34.035899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:34.035899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w2ciTpFKyolxOzpqRdeswkOTtH1fwjv8jP3VQ3fSDSAJlsto3hPEeKEPD43fv7wCqAnkPgCPsPS2DraOavA3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:34.036418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39fbdca9691a243fee59e6e23821db558c6c3429e9f4328400b0f5eb8938229d","sha256:c4c7768a53df1a69a3ce933b60f6ba37e4cbbdabc0cc1c103a6612d30e11dcf6"],"state_sha256":"ff399315865960b2a3dda4dd5b1e7732ccd88abeff616d4fc17aebd421e3ea8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jCZkNv6R/4T2AkX7DwrlCDxjPOq0u1Es0/h4VGpT1AG5ByYWG9wq5DkmTw2P4xVyR0uBkJ0O9IqBeln3A/8hBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:10:29.423594Z","bundle_sha256":"ce3fe343aa9eae2a62788ea587be72414df073dbb740fe9328c46180d5985107"}}