{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JI6DXJXC2NON6MZQPMITSXN656","short_pith_number":"pith:JI6DXJXC","canonical_record":{"source":{"id":"2312.14134","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T18:55:05Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"2ca881669fa6c2a7c957fe38b2c6c8e4221aa6bafa1205436adcdafcc4475555","abstract_canon_sha256":"ee03fcb92548e5dab2f9dca53c3d93c99495810f98be3fa2ea0f425bf9ec9b42"},"schema_version":"1.0"},"canonical_sha256":"4a3c3ba6e2d35cdf33307b11395dbeefbd7eb6f1f106b0627c9f8688f3dc4077","source":{"kind":"arxiv","id":"2312.14134","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14134","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14134v3","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14134","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"JI6DXJXC2NON","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"JI6DXJXC2NON6MZQ","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"JI6DXJXC","created_at":"2026-07-05T08:53:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JI6DXJXC2NON6MZQPMITSXN656","target":"record","payload":{"canonical_record":{"source":{"id":"2312.14134","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T18:55:05Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"2ca881669fa6c2a7c957fe38b2c6c8e4221aa6bafa1205436adcdafcc4475555","abstract_canon_sha256":"ee03fcb92548e5dab2f9dca53c3d93c99495810f98be3fa2ea0f425bf9ec9b42"},"schema_version":"1.0"},"canonical_sha256":"4a3c3ba6e2d35cdf33307b11395dbeefbd7eb6f1f106b0627c9f8688f3dc4077","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:38.656977Z","signature_b64":"yR/hs4B9BA+tAeMdFTuMWjVBZFIJDkRIsWloTy4t4+sLEB5DNWX/gWZ5lg5ZQdCAcUNGHmf7os6dTPhQMDT9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3c3ba6e2d35cdf33307b11395dbeefbd7eb6f1f106b0627c9f8688f3dc4077","last_reissued_at":"2026-07-05T08:53:38.656530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:38.656530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.14134","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":"2026-07-05T08:53:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVW+35AXL90ZxAi07KZ8AjWzm9DrNsCyV9NJrpFVk4RUzduCiitAwa442q8ZS0EP4Y5oVIxNCtwP7FyImYCxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:50:47.511302Z"},"content_sha256":"7ec29606d91650b08f06ea3987d847ac90559586e71eb50950c600297673c05b","schema_version":"1.0","event_id":"sha256:7ec29606d91650b08f06ea3987d847ac90559586e71eb50950c600297673c05b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JI6DXJXC2NON6MZQPMITSXN656","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Guangqi Jiang, Huazhe Xu, Tao Huang, Yanjie Ze","submitted_at":"2023-12-21T18:55:05Z","abstract_excerpt":"Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning (RL) tasks. In this work, we propose Diffusion Reward, a novel framework that learns rewards from expert videos via conditional video diffusion models for solving complex visual RL problems. Our key insight is that lower generative diversity is exhibited when conditioning diffusion on expert trajectories. Diffusion Reward is accordingly formalized by the negative of conditional entropy that encourages productive exploration of expert behaviors. We show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14134","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/2312.14134/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":"2026-07-05T08:53:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jnwxjRkIYjqBdTVtqWIqEGIESnL+b6QblAfFkktSKQ1Lng5Ki12LZnemAiawy/dtCqz6zu4n94OcXvpNjdc7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:50:47.512626Z"},"content_sha256":"ff5dbe85911c99eead282c604b4dda6feb7a66990de4eff50e36f7a24a284960","schema_version":"1.0","event_id":"sha256:ff5dbe85911c99eead282c604b4dda6feb7a66990de4eff50e36f7a24a284960"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JI6DXJXC2NON6MZQPMITSXN656/bundle.json","state_url":"https://pith.science/pith/JI6DXJXC2NON6MZQPMITSXN656/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JI6DXJXC2NON6MZQPMITSXN656/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":"2026-08-04T17:50:47Z","links":{"resolver":"https://pith.science/pith/JI6DXJXC2NON6MZQPMITSXN656","bundle":"https://pith.science/pith/JI6DXJXC2NON6MZQPMITSXN656/bundle.json","state":"https://pith.science/pith/JI6DXJXC2NON6MZQPMITSXN656/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JI6DXJXC2NON6MZQPMITSXN656/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JI6DXJXC2NON6MZQPMITSXN656","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":"ee03fcb92548e5dab2f9dca53c3d93c99495810f98be3fa2ea0f425bf9ec9b42","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T18:55:05Z","title_canon_sha256":"2ca881669fa6c2a7c957fe38b2c6c8e4221aa6bafa1205436adcdafcc4475555"},"schema_version":"1.0","source":{"id":"2312.14134","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14134","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14134v3","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14134","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"JI6DXJXC2NON","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"JI6DXJXC2NON6MZQ","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"JI6DXJXC","created_at":"2026-07-05T08:53:38Z"}],"graph_snapshots":[{"event_id":"sha256:ff5dbe85911c99eead282c604b4dda6feb7a66990de4eff50e36f7a24a284960","target":"graph","created_at":"2026-07-05T08:53:38Z","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/2312.14134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning (RL) tasks. In this work, we propose Diffusion Reward, a novel framework that learns rewards from expert videos via conditional video diffusion models for solving complex visual RL problems. Our key insight is that lower generative diversity is exhibited when conditioning diffusion on expert trajectories. Diffusion Reward is accordingly formalized by the negative of conditional entropy that encourages productive exploration of expert behaviors. We show th","authors_text":"Guangqi Jiang, Huazhe Xu, Tao Huang, Yanjie Ze","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T18:55:05Z","title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14134","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":"sha256:7ec29606d91650b08f06ea3987d847ac90559586e71eb50950c600297673c05b","target":"record","created_at":"2026-07-05T08:53:38Z","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":"ee03fcb92548e5dab2f9dca53c3d93c99495810f98be3fa2ea0f425bf9ec9b42","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T18:55:05Z","title_canon_sha256":"2ca881669fa6c2a7c957fe38b2c6c8e4221aa6bafa1205436adcdafcc4475555"},"schema_version":"1.0","source":{"id":"2312.14134","kind":"arxiv","version":3}},"canonical_sha256":"4a3c3ba6e2d35cdf33307b11395dbeefbd7eb6f1f106b0627c9f8688f3dc4077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a3c3ba6e2d35cdf33307b11395dbeefbd7eb6f1f106b0627c9f8688f3dc4077","first_computed_at":"2026-07-05T08:53:38.656530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:38.656530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yR/hs4B9BA+tAeMdFTuMWjVBZFIJDkRIsWloTy4t4+sLEB5DNWX/gWZ5lg5ZQdCAcUNGHmf7os6dTPhQMDT9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:38.656977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14134","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec29606d91650b08f06ea3987d847ac90559586e71eb50950c600297673c05b","sha256:ff5dbe85911c99eead282c604b4dda6feb7a66990de4eff50e36f7a24a284960"],"state_sha256":"e245ba9e547f7a8c2d7e5f3644a1d40aaca52a33ad9965e81da3c3aa018904cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ro5/j/bbBekQeeZKAoJnQDTp5w+rHIpQuXOPs65CTReOaYYjn/WrxN/Dp8EKUM2t2t4O49TU/fVyb5nijdn8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:50:47.540093Z","bundle_sha256":"d55a40328b7451d521b727464e87617672d13469fdcbf08c339dd128cfb3981a"}}