{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BMJUJRTNRUI23I224WN7BRMEQ5","short_pith_number":"pith:BMJUJRTN","canonical_record":{"source":{"id":"2510.02561","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-02T20:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8890417e3fe71c8641d30439d4b1b533dfdc9d6e8c9433f9f186d4496846df8a","abstract_canon_sha256":"783db7e2c856fe48c6e44cabe05daefc06e57a3015b9dbd748dc76e6439ee7b3"},"schema_version":"1.0"},"canonical_sha256":"0b1344c66d8d11ada35ae59bf0c5848757213bf000d13e8705ee2096b7ccd175","source":{"kind":"arxiv","id":"2510.02561","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.02561","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.02561v2","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02561","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"BMJUJRTNRUI2","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"BMJUJRTNRUI23I22","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"BMJUJRTN","created_at":"2026-06-23T02:13:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BMJUJRTNRUI23I224WN7BRMEQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2510.02561","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-02T20:57:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8890417e3fe71c8641d30439d4b1b533dfdc9d6e8c9433f9f186d4496846df8a","abstract_canon_sha256":"783db7e2c856fe48c6e44cabe05daefc06e57a3015b9dbd748dc76e6439ee7b3"},"schema_version":"1.0"},"canonical_sha256":"0b1344c66d8d11ada35ae59bf0c5848757213bf000d13e8705ee2096b7ccd175","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:17.335594Z","signature_b64":"gsdk8CGgqet0Us8dgaMHEVdXgvFNSi4W5lygvf+46JUZqY8sqa2He1UDiZmnsGUYPmZrFFoB4Vkxm3nKCrotDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b1344c66d8d11ada35ae59bf0c5848757213bf000d13e8705ee2096b7ccd175","last_reissued_at":"2026-06-23T02:13:17.335159Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:17.335159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.02561","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":"2026-06-23T02:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nkPRvX6iOtIu7vUwzKHIHCQ6AGZR0pye74UKhZWUkGmsZiI0ZQWSkKw4zRp+S6Z+OYGjtGu8Fi2O+uNOiEqSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:03:15.755235Z"},"content_sha256":"beabdc3c288b7a1f410c6bc9c238a895a6e25fefc13af864c514fd3a5475efb3","schema_version":"1.0","event_id":"sha256:beabdc3c288b7a1f410c6bc9c238a895a6e25fefc13af864c514fd3a5475efb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BMJUJRTNRUI23I224WN7BRMEQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Christine Klymko, Derek Shi, Felipe Leno da Silva, Hongjun Choi, Ruben Glatt, Sam Sakla, Shashank Kushwaha, Shubham Mohole","submitted_at":"2025-10-02T20:57:10Z","abstract_excerpt":"Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (SFT) with reinforcement learning from preference data to enhance video comprehension. However, as VLMs scale in parameter size, so does the cost of gathering enough human feedback. To make fine-tuning more cost-effective, recent frameworks explore reinforcement learning with AI feedback (RLAIF), which replace human preference with AI as a judge. Current RLAIF frameworks rely on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02561","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/2510.02561/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":"2026-06-23T02:13:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mruXgnqL7q7btRPg4j32oaiQTtuQDczj7mwPi6BGX8a1+ttbaxq/D/B8OcPdWrlQFcojSPWFnhL1PGajsXd2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:03:15.755627Z"},"content_sha256":"6ae4761cfb5cacf98d038fea734706b7fc59b841aa5c73dd2921ac80fcb67111","schema_version":"1.0","event_id":"sha256:6ae4761cfb5cacf98d038fea734706b7fc59b841aa5c73dd2921ac80fcb67111"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMJUJRTNRUI23I224WN7BRMEQ5/bundle.json","state_url":"https://pith.science/pith/BMJUJRTNRUI23I224WN7BRMEQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMJUJRTNRUI23I224WN7BRMEQ5/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":"2026-07-07T10:03:15Z","links":{"resolver":"https://pith.science/pith/BMJUJRTNRUI23I224WN7BRMEQ5","bundle":"https://pith.science/pith/BMJUJRTNRUI23I224WN7BRMEQ5/bundle.json","state":"https://pith.science/pith/BMJUJRTNRUI23I224WN7BRMEQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMJUJRTNRUI23I224WN7BRMEQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BMJUJRTNRUI23I224WN7BRMEQ5","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":"783db7e2c856fe48c6e44cabe05daefc06e57a3015b9dbd748dc76e6439ee7b3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-02T20:57:10Z","title_canon_sha256":"8890417e3fe71c8641d30439d4b1b533dfdc9d6e8c9433f9f186d4496846df8a"},"schema_version":"1.0","source":{"id":"2510.02561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.02561","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.02561v2","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02561","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_12","alias_value":"BMJUJRTNRUI2","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_16","alias_value":"BMJUJRTNRUI23I22","created_at":"2026-06-23T02:13:17Z"},{"alias_kind":"pith_short_8","alias_value":"BMJUJRTN","created_at":"2026-06-23T02:13:17Z"}],"graph_snapshots":[{"event_id":"sha256:6ae4761cfb5cacf98d038fea734706b7fc59b841aa5c73dd2921ac80fcb67111","target":"graph","created_at":"2026-06-23T02:13:17Z","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/2510.02561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large video-language models (VLMs) rely on extensive fine-tuning techniques that strengthen alignment between textual and visual comprehension. Leading pipelines typically pair supervised fine-tuning (SFT) with reinforcement learning from preference data to enhance video comprehension. However, as VLMs scale in parameter size, so does the cost of gathering enough human feedback. To make fine-tuning more cost-effective, recent frameworks explore reinforcement learning with AI feedback (RLAIF), which replace human preference with AI as a judge. Current RLAIF frameworks rely on","authors_text":"Christine Klymko, Derek Shi, Felipe Leno da Silva, Hongjun Choi, Ruben Glatt, Sam Sakla, Shashank Kushwaha, Shubham Mohole","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-02T20:57:10Z","title":"Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02561","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:beabdc3c288b7a1f410c6bc9c238a895a6e25fefc13af864c514fd3a5475efb3","target":"record","created_at":"2026-06-23T02:13:17Z","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":"783db7e2c856fe48c6e44cabe05daefc06e57a3015b9dbd748dc76e6439ee7b3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-02T20:57:10Z","title_canon_sha256":"8890417e3fe71c8641d30439d4b1b533dfdc9d6e8c9433f9f186d4496846df8a"},"schema_version":"1.0","source":{"id":"2510.02561","kind":"arxiv","version":2}},"canonical_sha256":"0b1344c66d8d11ada35ae59bf0c5848757213bf000d13e8705ee2096b7ccd175","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b1344c66d8d11ada35ae59bf0c5848757213bf000d13e8705ee2096b7ccd175","first_computed_at":"2026-06-23T02:13:17.335159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:17.335159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gsdk8CGgqet0Us8dgaMHEVdXgvFNSi4W5lygvf+46JUZqY8sqa2He1UDiZmnsGUYPmZrFFoB4Vkxm3nKCrotDA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:17.335594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.02561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beabdc3c288b7a1f410c6bc9c238a895a6e25fefc13af864c514fd3a5475efb3","sha256:6ae4761cfb5cacf98d038fea734706b7fc59b841aa5c73dd2921ac80fcb67111"],"state_sha256":"968d60446534c6630b595ad60c32b3875d16f55170106721fe7b0e7a2aebea18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zDauitM2hRyk+3A/EYi29fWwuROoZHRsDo96oT2lhd5PGcGObRYx+VWekAXLjR0K5Mw3azywAXR5kmFgtboyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:03:15.757591Z","bundle_sha256":"ebbb36ab4c802205e5593b55c73c336e8664f5acbeaf1ef47654c7778132a5d4"}}