{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JNMCIG3CW4YHRE2JGZQQC24PH6","short_pith_number":"pith:JNMCIG3C","canonical_record":{"source":{"id":"2009.12604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:09:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f11103666824a40c5bed85be48941db472415c929f2afb127542a0c8b746c2c4","abstract_canon_sha256":"9c73523bb9e6686967f3ec2af54163a781413e1b73c9dc3b52217538aac2770a"},"schema_version":"1.0"},"canonical_sha256":"4b58241b62b7307893493661016b8f3f967c9a5aaff120c6602805bd9d604fed","source":{"kind":"arxiv","id":"2009.12604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12604","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12604v1","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12604","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"pith_short_12","alias_value":"JNMCIG3CW4YH","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"pith_short_16","alias_value":"JNMCIG3CW4YHRE2J","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"pith_short_8","alias_value":"JNMCIG3C","created_at":"2026-07-05T01:38:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JNMCIG3CW4YHRE2JGZQQC24PH6","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:09:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f11103666824a40c5bed85be48941db472415c929f2afb127542a0c8b746c2c4","abstract_canon_sha256":"9c73523bb9e6686967f3ec2af54163a781413e1b73c9dc3b52217538aac2770a"},"schema_version":"1.0"},"canonical_sha256":"4b58241b62b7307893493661016b8f3f967c9a5aaff120c6602805bd9d604fed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:21.719541Z","signature_b64":"K/30yMaAWLk3eACG2nv000nFqY+OH9UPAgun6uzyunfVUn1JLlFauf2ZJRRq9gHIVX9/LUtVW2ldOGiE4iiKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b58241b62b7307893493661016b8f3f967c9a5aaff120c6602805bd9d604fed","last_reissued_at":"2026-07-05T01:38:21.719110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:21.719110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12604","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":"2026-07-05T01:38:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFrsGG5k81zGV6vE5ybWVgYS4O5jsHU084Whh9q/bhI/i28KZYwjQYFbCwCdSKMxlaidgyQ9MC1B37MjpB8tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:03:49.769895Z"},"content_sha256":"bff57182555afcd2f21455b733f7d93254441ae24038fb79910af32fe5a4eb86","schema_version":"1.0","event_id":"sha256:bff57182555afcd2f21455b733f7d93254441ae24038fb79910af32fe5a4eb86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JNMCIG3CW4YHRE2JGZQQC24PH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph neural induction of value iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreea Deac, Jian Tang, Pierre-Luc Bacon","submitted_at":"2020-09-26T14:09:16Z","abstract_excerpt":"Many reinforcement learning tasks can benefit from explicit planning based on an internal model of the environment. Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration. Such network have so far been focused on restrictive environments (e.g. grid-worlds), and modelled the planning procedure only indirectly. We relax these constraints, proposing a graph neural network (GNN) that executes the value iteration (VI) algorithm, across arbitrary environment models, with direct supervision on the inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12604","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/2009.12604/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":"2026-07-05T01:38:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/rBTHghiGORZsquQws6RKySvjEk4M6k7Bjdbof3nZv4rGGvA/vuulS0yOO6veNfqhi0fKbdvX7CWVjQx20S+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:03:49.770463Z"},"content_sha256":"1dc5e39619f21c455cbce7f1087ebac0216316e86b1f4f048e63251b3d4c8ec4","schema_version":"1.0","event_id":"sha256:1dc5e39619f21c455cbce7f1087ebac0216316e86b1f4f048e63251b3d4c8ec4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JNMCIG3CW4YHRE2JGZQQC24PH6/bundle.json","state_url":"https://pith.science/pith/JNMCIG3CW4YHRE2JGZQQC24PH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JNMCIG3CW4YHRE2JGZQQC24PH6/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":"2026-08-19T23:03:49Z","links":{"resolver":"https://pith.science/pith/JNMCIG3CW4YHRE2JGZQQC24PH6","bundle":"https://pith.science/pith/JNMCIG3CW4YHRE2JGZQQC24PH6/bundle.json","state":"https://pith.science/pith/JNMCIG3CW4YHRE2JGZQQC24PH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JNMCIG3CW4YHRE2JGZQQC24PH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JNMCIG3CW4YHRE2JGZQQC24PH6","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":"9c73523bb9e6686967f3ec2af54163a781413e1b73c9dc3b52217538aac2770a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:09:16Z","title_canon_sha256":"f11103666824a40c5bed85be48941db472415c929f2afb127542a0c8b746c2c4"},"schema_version":"1.0","source":{"id":"2009.12604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12604","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12604v1","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12604","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"pith_short_12","alias_value":"JNMCIG3CW4YH","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"pith_short_16","alias_value":"JNMCIG3CW4YHRE2J","created_at":"2026-07-05T01:38:21Z"},{"alias_kind":"pith_short_8","alias_value":"JNMCIG3C","created_at":"2026-07-05T01:38:21Z"}],"graph_snapshots":[{"event_id":"sha256:1dc5e39619f21c455cbce7f1087ebac0216316e86b1f4f048e63251b3d4c8ec4","target":"graph","created_at":"2026-07-05T01:38:21Z","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/2009.12604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many reinforcement learning tasks can benefit from explicit planning based on an internal model of the environment. Previously, such planning components have been incorporated through a neural network that partially aligns with the computational graph of value iteration. Such network have so far been focused on restrictive environments (e.g. grid-worlds), and modelled the planning procedure only indirectly. We relax these constraints, proposing a graph neural network (GNN) that executes the value iteration (VI) algorithm, across arbitrary environment models, with direct supervision on the inte","authors_text":"Andreea Deac, Jian Tang, Pierre-Luc Bacon","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:09:16Z","title":"Graph neural induction of value iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12604","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:bff57182555afcd2f21455b733f7d93254441ae24038fb79910af32fe5a4eb86","target":"record","created_at":"2026-07-05T01:38:21Z","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":"9c73523bb9e6686967f3ec2af54163a781413e1b73c9dc3b52217538aac2770a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-26T14:09:16Z","title_canon_sha256":"f11103666824a40c5bed85be48941db472415c929f2afb127542a0c8b746c2c4"},"schema_version":"1.0","source":{"id":"2009.12604","kind":"arxiv","version":1}},"canonical_sha256":"4b58241b62b7307893493661016b8f3f967c9a5aaff120c6602805bd9d604fed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b58241b62b7307893493661016b8f3f967c9a5aaff120c6602805bd9d604fed","first_computed_at":"2026-07-05T01:38:21.719110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:38:21.719110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/30yMaAWLk3eACG2nv000nFqY+OH9UPAgun6uzyunfVUn1JLlFauf2ZJRRq9gHIVX9/LUtVW2ldOGiE4iiKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:38:21.719541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bff57182555afcd2f21455b733f7d93254441ae24038fb79910af32fe5a4eb86","sha256:1dc5e39619f21c455cbce7f1087ebac0216316e86b1f4f048e63251b3d4c8ec4"],"state_sha256":"15d51ddd67c7aef16e049f85a0543e3d34b7f3a47a7d3590170396bcd5f591f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BKQHzVYzehwKJNSL11KHXyLc4s/C0qGzA1tmjhuXki7sEcgHiFULLiOZEXpB4UPxQzeb6pfz9PJsrPNz4qRuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:03:49.775088Z","bundle_sha256":"da86d8ff3adb1a6fc41e9e839b90c2d7bd3704a6eb9f5b62594cf3ec05425ee1"}}